Paper Digest: Recent Papers on Question Answering
Paper Digest Team extracted all recent Question Answering related papers on our radar, and generated highlight sentences for them. The results are then sorted by relevance & date. In addition to this ‘static’ page, we also provide a real-time version of this article, which has more coverage and is updated in real time to include the most recent updates on this topic.
Based in New York, Paper Digest is dedicated to producing high-quality text analysis results that people can acturally use on a daily basis. Since 2018, we have been serving users across the world with a number of exclusive services to track, search, review and rewrite scientific literature.
You are welcome to follow us on Twitter and Linkedin to get updated with new conference digests.
Paper Digest Team
New York City, New York, 10017
team@paperdigest.org
TABLE 1: Paper Digest: Recent Papers on Question Answering
Paper | Author(s) | Source | Date | |
---|---|---|---|---|
1 | Language Model Knowledge Distillation for Efficient Question Answering in Spanish Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Therefore, smaller distilled models for the Spanish language could be proven to be highly scalable and facilitate their further adoption on a variety of tasks and scenarios. In this work, we take one step in this direction by developing SpanishTinyRoBERTa, a compressed language model based on RoBERTa for efficient question answering in Spanish. |
Adrián Bazaga; Pietro Liò; Gos Micklem; | arxiv-cs.CL | 2023-12-07 |
2 | PCoQA: Persian Conversational Question Answering Dataset Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In the pursuit of conversational question answering research, we introduce the PCoQA, the first \textbf{P}ersian \textbf{Co}nversational \textbf{Q}uestion \textbf{A}nswering dataset, a resource comprising information-seeking dialogs encompassing a total of 9,026 contextually-driven questions. |
HAMED HEMATIAN HEMATI et. al. | arxiv-cs.CL | 2023-12-07 |
3 | XAIQA: Explainer-Based Data Augmentation for Extractive Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce a novel approach, XAIQA, for generating synthetic QA pairs at scale from data naturally available in electronic health records. |
JOEL STREMMEL et. al. | arxiv-cs.CL | 2023-12-06 |
4 | Let The LLMs Talk: Simulating Human-to-Human Conversational QA Via Zero-Shot LLM-to-LLM Interactions Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Despite its effectiveness, challenges exist as human annotation is time-consuming, inconsistent, and not scalable. To address this issue and investigate the applicability of large language models (LLMs) in CQA simulation, we propose a simulation framework that employs zero-shot learner LLMs for simulating teacher-student interactions. |
Zahra Abbasiantaeb; Yifei Yuan; Evangelos Kanoulas; Mohammad Aliannejadi; | arxiv-cs.CL | 2023-12-05 |
5 | Unleashing The Potential of Large Language Model: Zero-shot VQA for Flood Disaster Scenario Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a zero-shot VQA model named Zero-shot VQA for Flood Disaster Damage Assessment (ZFDDA). |
Yimin Sun; Chao Wang; Yan Peng; | arxiv-cs.CV | 2023-12-04 |
6 | VaQuitA: Enhancing Alignment in LLM-Assisted Video Understanding Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In our study, we introduce a cutting-edge framework, VaQuitA, designed to refine the synergy between video and textual information. |
YIZHOU WANG et. al. | arxiv-cs.CV | 2023-12-04 |
7 | GNN2R: Weakly-Supervised Rationale-Providing Question Answering Over Knowledge Graphs Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Second, it is difficult to maintain high efficiency when explicit KG triples need to be retrieved to generate explanations. In this paper, we propose a novel Graph Neural Network-based Two-Step Reasoning model (GNN2R) to solve this issue. |
Ruijie Wang; Luca Rossetto; Michael Cochez; Abraham Bernstein; | arxiv-cs.CL | 2023-12-04 |
8 | How to Configure Good In-Context Sequence for Visual Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To enhance the ICL performance, in this study, we use Visual Question Answering (VQA) as case study to explore diverse in-context configurations to find the powerful ones. |
Li Li; Jiawei Peng; Huiyi Chen; Chongyang Gao; Xu Yang; | arxiv-cs.CV | 2023-12-03 |
9 | Towards Leveraging LLMs for Conditional QA Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Utilizing the Conditional Question Answering (CQA) dataset and focusing on generative models like T5 and UL2, we assess the performance of LLMs across diverse question types. |
Syed-Amad Hussain; Parag Pravin Dakle; SaiKrishna Rallabandi; Preethi Raghavan; | arxiv-cs.CL | 2023-12-02 |
10 | Harnessing The Power of Prompt-based Techniques for Generating School-Level Questions Using Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we propose a novel approach that utilizes prompt-based techniques to generate descriptive and reasoning-based questions. |
Subhankar Maity; Aniket Deroy; Sudeshna Sarkar; | arxiv-cs.CL | 2023-12-02 |
11 | Zero-Shot Video Question Answering with Procedural Programs Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose to answer zero-shot questions about videos by generating short procedural programs that derive a final answer from solving a sequence of visual subtasks. |
Rohan Choudhury; Koichiro Niinuma; Kris M. Kitani; László A. Jeni; | arxiv-cs.CV | 2023-12-01 |
12 | ESG Accountability Made Easy: DocQA at Your Service Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Users can explore over 10,000 Environmental, Social, and Governance (ESG) disclosure reports from over 2000 corporations. |
LOKESH MISHRA et. al. | arxiv-cs.CL | 2023-11-30 |
13 | Enhancing Answer Selection in Community Question Answering with Pre-trained and Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Specifically, we apply the BERT model as the encoder layer to do pre-training for question subjects, question bodies and answers, respectively, then the cross attention mechanism selects the most relevant answer for different questions. |
Xinghang Hu; | arxiv-cs.CL | 2023-11-29 |
14 | AviationGPT: A Large Language Model for The Aviation Domain Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The emergence of LLMs presents an opportunity to transform this situation, but there is a lack of LLMs specifically designed for the aviation domain. To address this gap, we propose AviationGPT, which is built on open-source LLaMA-2 and Mistral architectures and continuously trained on a wealth of carefully curated aviation datasets. |
Liya Wang; Jason Chou; Xin Zhou; Alex Tien; Diane M Baumgartner; | arxiv-cs.CL | 2023-11-29 |
15 | Uncertainty Guided Global Memory Improves Multi-Hop Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, attention-based token representations lack explicit global contextual information to connect reasoning steps. To address these issues, we propose GEMFormer, a two-stage method that first collects relevant information over the entire document to the memory and then combines it with local context to solve the task. |
Alsu Sagirova; Mikhail Burtsev; | arxiv-cs.CL | 2023-11-29 |
16 | Towards Top-Down Reasoning: An Explainable Multi-Agent Approach for Visual Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Moreover, the existing VQA methods that rely on Knowledge Bases (KBs) might frequently encounter biases from limited data and face challenges in relevant information indexing. Attempt to overcome these limitations, this paper introduces an explainable multi-agent collaboration framework by tapping into knowledge embedded in Large Language Models (LLMs) trained on extensive corpora. |
ZEQING WANG et. al. | arxiv-cs.CV | 2023-11-28 |
17 | Fully Authentic Visual Question Answering Dataset from Online Communities Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce the first VQA dataset in which all contents originate from an authentic use case. |
CHONGYAN CHEN et. al. | arxiv-cs.CV | 2023-11-27 |
18 | Releasing The CRaQAn (Coreference Resolution in Question-Answering): An Open-source Dataset and Dataset Creation Methodology Using Instruction-following Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work we present our Coreference Resolution in Question-Answering (CRaQAn) dataset, an open-source dataset that caters to the nuanced information retrieval requirements of coreference resolution in question-answering tasks by providing over 250 question-answer pairs containing coreferences. |
ROB GRZYWINSKI et. al. | arxiv-cs.CL | 2023-11-27 |
19 | Characterizing Video Question Answering with Sparsified Inputs Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this way, we experiment over public VideoQA benchmarks and provide analysis on how sparsified inputs affect the performance. |
Shiyuan Huang; Robinson Piramuthu; Vicente Ordonez; Shih-Fu Chang; Gunnar A. Sigurdsson; | arxiv-cs.CV | 2023-11-27 |
20 | Uncertainty-aware Language Modeling for Selective Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present an automatic large language model (LLM) conversion approach that produces uncertainty-aware LLMs capable of estimating uncertainty with every prediction. |
QI YANG et. al. | arxiv-cs.CL | 2023-11-26 |
21 | Optimizing and Fine-tuning Large Language Model for Urban Renewal Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This study aims to innovatively explore adaptive applications of large language models (LLM) in urban renewal. |
XI WANG et. al. | arxiv-cs.CL | 2023-11-26 |
22 | See and Think: Embodied Agent in Virtual Environment Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose STEVE, a comprehensive and visionary embodied agent in the Minecraft virtual environment. |
ZHONGHAN ZHAO et. al. | arxiv-cs.AI | 2023-11-26 |
23 | A Comparative and Experimental Study on Automatic Question Answering Systems and Its Robustness Against Word Jumbling Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Question answer generation using Natural Language Processing models is ubiquitous in the world around us. |
Shashidhar Reddy Javaji; Haoran Hu; Sai Sameer Vennam; Vijaya Gajanan Buddhavarapu; | arxiv-cs.CL | 2023-11-26 |
24 | AutoEval-Video: An Automatic Benchmark for Assessing Large Vision Language Models in Open-Ended Video Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We propose a novel and challenging benchmark, AutoEval-Video, to comprehensively evaluate large vision-language models in open-ended video question answering. |
Xiuyuan Chen; Yuan Lin; Yuchen Zhang; Weiran Huang; | arxiv-cs.CV | 2023-11-24 |
25 | Probabilistic Tree-of-thought Reasoning for Answering Knowledge-intensive Complex Questions Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a novel approach: Probabilistic Tree-of-thought Reasoning (ProbTree). |
SHULIN CAO et. al. | arxiv-cs.CL | 2023-11-23 |
26 | Question Answering in Natural Language: The Special Case of Temporal Expressions Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Our work aims to leverage a popular approach used for general question answering, answer extraction, in order to find answers to temporal questions within a paragraph. |
Armand Stricker; | arxiv-cs.CL | 2023-11-23 |
27 | Drilling Down Into The Discourse Structure with LLMs for Long Document Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We aim to assess the applicability of large language models (LLMs) in the task of zero-shot long document evidence retrieval, owing to their unprecedented performance across various NLP tasks. |
Inderjeet Nair; Shwetha Somasundaram; Apoorv Saxena; Koustava Goswami; | arxiv-cs.CL | 2023-11-22 |
28 | FinanceBench: A New Benchmark for Financial Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We test 16 state of the art model configurations (including GPT-4-Turbo, Llama2 and Claude2, with vector stores and long context prompts) on a sample of 150 cases from FinanceBench, and manually review their answers (n=2,400). |
PRANAB ISLAM et. al. | arxiv-cs.CL | 2023-11-20 |
29 | Taiyi: A Bilingual Fine-Tuned Large Language Model for Diverse Biomedical Tasks Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we first curated a comprehensive collection of 140 existing biomedical text mining datasets across over 10 task types. |
LING LUO et. al. | arxiv-cs.CL | 2023-11-20 |
30 | PEFT-MedAware: Large Language Model for Medical Awareness Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Chat models are capable of answering a wide range of questions, however, the accuracy of their responses is highly uncertain. In this research, we propose a specialized PEFT-MedAware model where we utilize parameter-efficient fine-tuning (PEFT) to enhance the Falcon-1b large language model on specialized MedQuAD data consisting of 16,407 medical QA pairs, leveraging only 0.44% of its trainable parameters to enhance computational efficiency. |
Keivalya Pandya; | arxiv-cs.CL | 2023-11-17 |
31 | Towards Robust Temporal Reasoning of Large Language Models Via A Multi-Hop QA Dataset and Pseudo-Instruction Tuning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a complex temporal question-answering (QA) dataset Complex-TR that focuses on multi-answer and multi-hop temporal reasoning. |
Qingyu Tan; Hwee Tou Ng; Lidong Bing; | arxiv-cs.CL | 2023-11-16 |
32 | Leveraging LLMs in Scholarly Knowledge Graph Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: This paper presents a scholarly Knowledge Graph Question Answering (KGQA) that answers bibliographic natural language questions by leveraging a large language model (LLM) in a few-shot manner. |
Tilahun Abedissa Taffa; Ricardo Usbeck; | arxiv-cs.CL | 2023-11-16 |
33 | Crafting In-context Examples According to LMs’ Parametric Knowledge Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We perform analysis on three multi-answer question answering datasets, which allows us to further study answer set ordering strategies based on the LM’s knowledge about each answer. |
Yoonsang Lee; Pranav Atreya; Xi Ye; Eunsol Choi; | arxiv-cs.CL | 2023-11-16 |
34 | Graph-Guided Reasoning for Multi-Hop Question Answering in Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To address them, we propose a graph-guided CoT prompting method, which guides the LLMs to reach the correct answer with graph representation/verification steps. |
Jinyoung Park; Ameen Patel; Omar Zia Khan; Hyunwoo J. Kim; Joo-Kyung Kim; | arxiv-cs.CL | 2023-11-16 |
35 | On Evaluating The Integration of Reasoning and Action in LLM Agents with Database Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To address the challenge of accurately assessing answer quality, we introduce a multi-agent evaluation framework that simulates the academic peer-review process, enhancing the precision and reliability of our evaluations. |
LINYONG NAN et. al. | arxiv-cs.CL | 2023-11-16 |
36 | FairytaleCQA: Integrating A Commonsense Knowledge Graph Into Children’s Storybook Narratives Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce the FairytaleCQA dataset, which is annotated by children education experts, to supplement 278 storybook narratives with educationally appropriate commonsense knowledge. |
JIAJU CHEN et. al. | arxiv-cs.CL | 2023-11-16 |
37 | Improving Zero-shot Visual Question Answering Via Large Language Models with Reasoning Question Prompts Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: To this end, we present Reasoning Question Prompts for VQA tasks, which can further activate the potential of LLMs in zero-shot scenarios. |
YUNSHI LAN et. al. | arxiv-cs.CV | 2023-11-15 |
38 | Reasoning Over Description Logic-based Contexts with Transformers Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we seek to answer the question how well a transformer-based model will perform reasoning over expressive contexts. |
Angelos Poulis; Eleni Tsalapati; Manolis Koubarakis; | arxiv-cs.CL | 2023-11-15 |
39 | Pachinko: Patching Interpretable QA Models Through Natural Language Feedback Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We sample these rationales from large language models using few-shot prompting for two reading comprehension datasets, and then perform two user studies. In the first one, we present users with incorrect answers and corresponding rationales of various formats and ask them to provide natural language feedback to revise the rationale. |
Chaitanya Malaviya; Subin Lee; Dan Roth; Mark Yatskar; | arxiv-cs.CL | 2023-11-15 |
40 | Towards Pragmatic Awareness in Question Answering: A Case Study in Maternal and Infant Health Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In a high-risk domain such as maternal and infant health, a question-answering system must recognize these pragmatic constraints and go beyond simply answering user questions, examining them in context to respond helpfully. To achieve this, we study pragmatic inferences made when mothers ask questions about pregnancy and infant care. |
Neha Srikanth; Rupak Sarkar; Rachel Rudinger; Jordan Boyd-Graber; | arxiv-cs.CL | 2023-11-15 |
41 | SQATIN: Supervised Instruction Tuning Meets Question Answering for Improved Dialogue NLU Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we introduce SQATIN, a new framework for dialog NLU based on (i) instruction tuning and (ii) question-answering-based formulation of ID and VE tasks. |
Evgeniia Razumovskaia; Goran Glavaš; Anna Korhonen; Ivan Vulić; | arxiv-cs.CL | 2023-11-15 |
42 | Combining Transfer Learning with In-context Learning Using Blackbox LLMs for Zero-shot Knowledge Base Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: More recently, few-shot in-context learning using Black-box Large Language Models (BLLMs) has been adapted for KBQA without considering any source domain data. In this work, we show how to meaningfully combine these two paradigms for KBQA so that their benefits add up. |
Mayur Patidar; Avinash Singh; Riya Sawhney; Indrajit Bhattacharya; | arxiv-cs.CL | 2023-11-15 |
43 | Long-form Question Answering: An Iterative Planning-Retrieval-Generation Approach Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Additionally, generating detailed long-form answers often entails aggregating knowledge from diverse sources. To address these limitations, we propose an LFQA model with iterative Planning, Retrieval, and Generation. |
Pritom Saha Akash; Kashob Kumar Roy; Lucian Popa; Kevin Chen-Chuan Chang; | arxiv-cs.CL | 2023-11-15 |
44 | Pinpoint, Not Criticize: Refining Large Language Models Via Fine-Grained Actionable Feedback Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we propose an inference time optimization method FITO to use fine-grained actionable feedback in the form of error type, error location and severity level that are predicted by a learned error pinpoint model for iterative refinement. |
WENDA XU et. al. | arxiv-cs.CL | 2023-11-15 |
45 | Temporal Knowledge Question Answering Via Abstract Reasoning Induction Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we tackle the significant challenge of temporal knowledge reasoning in Large Language Models (LLMs), an area where such models frequently encounter difficulties. |
Ziyang Chen; Dongfang Li; Xiang Zhao; Baotian Hu; Min Zhang; | arxiv-cs.CL | 2023-11-15 |
46 | Never Lost in The Middle: Improving Large Language Models Via Attention Strengthening Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The lost in the middle problem challenges most LLMs, referring to the dramatic decline in accuracy when correct information is located in the middle. To overcome this crucial issue, this paper proposes to enhance the information searching and reflection ability of LLMs in long contexts via specially designed tasks called Attention Strengthening Multi-doc QA (ASM QA). |
HE JUNQING et. al. | arxiv-cs.CL | 2023-11-15 |
47 | Asking More Informative Questions for Grounded Retrieval Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present an approach that formulates more informative, open-ended questions. |
Sedrick Keh; Justin T. Chiu; Daniel Fried; | arxiv-cs.CL | 2023-11-14 |
48 | Attribute Diversity Determines The Systematicity Gap in VQA Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we study the systematicity gap in visual question answering: the performance difference between reasoning on previously seen and unseen combinations of object attributes. |
Ian Berlot-Attwell; A. Michael Carrell; Kumar Krishna Agrawal; Yash Sharma; Naomi Saphra; | arxiv-cs.LG | 2023-11-14 |
49 | XplainLLM: A QA Explanation Dataset for Understanding LLM Decision-Making Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Despite their remarkable performance, understanding their decision-making process remains a big challenge. In this paper, we look into bringing some transparency to this process by introducing a new explanation dataset for question answering (QA) tasks that integrates knowledge graphs (KGs) in a novel way. |
Zichen Chen; Jianda Chen; Mitali Gaidhani; Ambuj Singh; Misha Sra; | arxiv-cs.CL | 2023-11-14 |
50 | Carpe Diem: On The Evaluation of World Knowledge in Lifelong Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Our work aims to model the dynamic nature of real-world information, offering a robust measure for the evolution-adaptability of language models. |
Yujin Kim; Jaehong Yoon; Seonghyeon Ye; Sung Ju Hwang; Se-young Yun; | arxiv-cs.CL | 2023-11-14 |
51 | Understanding Calibration for Multilingual Question Answering Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we study the calibration properties of several pre-trained multilingual large language models (LLMs) on a variety of question-answering tasks. |
Yahan Yang; Soham Dan; Dan Roth; Insup Lee; | arxiv-cs.CL | 2023-11-14 |
52 | Insights Into Classifying and Mitigating LLMs’ Hallucinations Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Our research addresses this critical issue within the HeReFaNMi (Health-Related Fake News Mitigation) project, generously supported by NGI Search, dedicated to combating Health-Related Fake News dissemination on the Internet. This endeavour represents a concerted effort to safeguard the integrity of information dissemination in an age of evolving AI technologies. |
Alessandro Bruno; Pier Luigi Mazzeo; Aladine Chetouani; Marouane Tliba; Mohamed Amine Kerkouri; | arxiv-cs.CL | 2023-11-14 |
53 | How Well Do Large Language Models Understand Syntax? An Evaluation By Asking Natural Language Questions Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: While recent advancements in large language models (LLMs) bring us closer to achieving artificial general intelligence, the question persists: Do LLMs truly understand language, or do they merely mimic comprehension through pattern recognition? This study seeks to explore this question through the lens of syntax, a crucial component of sentence comprehension. |
HOUQUAN ZHOU et. al. | arxiv-cs.CL | 2023-11-14 |
54 | Learning to Filter Context for Retrieval-Augmented Generation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: This can cause over- or under-reliance on context, and result in problems in the generated output such as hallucinations. To alleviate these problems, we propose FILCO, a method that improves the quality of the context provided to the generator by (1) identifying useful context based on lexical and information-theoretic approaches, and (2) training context filtering models that can filter retrieved contexts at test time. |
Zhiruo Wang; Jun Araki; Zhengbao Jiang; Md Rizwan Parvez; Graham Neubig; | arxiv-cs.CL | 2023-11-14 |
55 | TempTabQA: Temporal Question Answering for Semi-Structured Tables Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Can current NLP systems reason about such information in semi-structured tables? To tackle this question, we introduce the task of temporal question answering on semi-structured tables. |
VIVEK GUPTA et. al. | arxiv-cs.CL | 2023-11-14 |
56 | Semi-Structured Chain-of-Thought: Integrating Multiple Sources of Knowledge for Improved Language Model Reasoning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Most existing prompting methods either rely solely on one or two of these sources, or require repeatedly invoking large language models to generate similar or identical content. In this work, we overcome these limitations by introducing a novel semi-structured prompting approach that seamlessly integrates the model’s parametric memory with unstructured knowledge from text documents and structured knowledge from knowledge graphs. |
Xin Su; Tiep Le; Steven Bethard; Phillip Howard; | arxiv-cs.CL | 2023-11-14 |
57 | How Good Are Large Language Models on African Languages? Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present an analysis of three popular large language models (mT0, LLaMa 2, and GPT-4) on five tasks (news topic classification, sentiment classification, machine translation, question answering, and named entity recognition) across 30 African languages, spanning different language families and geographical regions. |
Jessica Ojo; Kelechi Ogueji; Pontus Stenetorp; David I. Adelani; | arxiv-cs.CL | 2023-11-14 |
58 | RECALL: A Benchmark for LLMs Robustness Against External Counterfactual Knowledge Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Our benchmark consists of two tasks, Question Answering and Text Generation, and for each task, we provide models with a context containing counterfactual information. |
YI LIU et. al. | arxiv-cs.CL | 2023-11-14 |
59 | CPopQA: Ranking Cultural Concept Popularity By LLMs Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: How well an LLM captures the corpus-level statistical trends of concepts for reasoning, especially long-tail ones, is still underexplored. In this study, we introduce a novel few-shot question-answering task (CPopQA) that examines LLMs’ statistical ranking abilities for long-tail cultural concepts (e.g., holidays), with a specific focus on these concepts’ popularity in the United States and the United Kingdom, respectively. |
Ming Jiang; Mansi Joshi; | arxiv-cs.CL | 2023-11-13 |
60 | A Comprehensive Evaluation of GPT-4V on Knowledge-Intensive Visual Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Yet, the true challenge lies in the domain of knowledge-intensive VQA tasks, which necessitate not just recognition of visual elements, but also a deep comprehension of the visual information in conjunction with a vast repository of learned knowledge. To uncover such capabilities of MLMs, particularly the newly introduced GPT-4V, we provide an in-depth evaluation from three perspectives: 1) Commonsense Knowledge, which assesses how well models can understand visual cues and connect to general knowledge; 2) Fine-grained World Knowledge, which tests the model’s skill in reasoning out specific knowledge from images, showcasing their proficiency across various specialized fields; 3) Comprehensive Knowledge with Decision-making Rationales, which examines model’s capability to provide logical explanations for its inference, facilitating a deeper analysis from the interpretability perspective. |
YUNXIN LI et. al. | arxiv-cs.CL | 2023-11-13 |
61 | A Benchmark to Understand The Role of Knowledge Graphs on Large Language Model’s Accuracy for Question Answering on Enterprise SQL Databases Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This study aims to evaluate the accuracy of LLM-powered question answering systems in the context of enterprise questions and SQL databases, while also exploring the role of knowledge graphs in improving accuracy. To achieve this, we introduce a benchmark comprising an enterprise SQL schema in the insurance domain, a range of enterprise queries encompassing reporting to metrics, and a contextual layer incorporating an ontology and mappings that define a knowledge graph. |
Juan Sequeda; Dean Allemang; Bryon Jacob; | arxiv-cs.AI | 2023-11-13 |
62 | Bring Your Own KG: Self-Supervised Program Synthesis for Zero-Shot KGQA Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We present BYOKG, a universal question-answering (QA) system that can operate on any knowledge graph (KG), requires no human-annotated training data, and can be ready to use within a day — attributes that are out-of-scope for current KGQA systems. |
Dhruv Agarwal; Rajarshi Das; Sopan Khosla; Rashmi Gangadharaiah; | arxiv-cs.CL | 2023-11-13 |
63 | Evaluating LLMs on Document-Based QA: Exact Answer Selection and Numerical Extraction Using Cogtale Dataset Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: While some existing work focus on evaluating large language model’s performance on retrieving and answering questions from documents, assessing the LLMs’ performance on QA types that require exact answer selection from predefined options and numerical extraction is yet to be fully assessed. In this paper, we specifically focus on this underexplored context and conduct empirical analysis of LLMs (GPT-4 and GPT 3.5) on question types, including single-choice, yes-no, multiple-choice, and number extraction questions from documents. |
ZAFARYAB RASOOL et. al. | arxiv-cs.IR | 2023-11-13 |
64 | Hallucination Augmented Recitations for Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose Hallucination Augmented Recitations (HAR) for creating counterfactual datasets by utilizing hallucination in LLMs to improve attribution. |
Abdullatif Köksal; Renat Aksitov; Chung-Ching Chang; | arxiv-cs.CL | 2023-11-13 |
65 | A Step Closer to Comprehensive Answers: Constrained Multi-Stage Question Decomposition with Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Challenges arise when these models grapple with understanding multi-hop relations in complex questions or lack the necessary knowledge for a comprehensive response. To address this issue, we introduce the Decompose-and-Query framework (D&Q). |
HEJING CAO et. al. | arxiv-cs.CL | 2023-11-13 |
66 | On The Robustness of Question Rewriting Systems to Questions of Varying Hardness Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we are interested in the robustness of a QR system to questions varying in rewriting hardness or difficulty. |
Hai Ye; Hwee Tou Ng; Wenjuan Han; | arxiv-cs.CL | 2023-11-12 |
67 | SELF-EXPLAIN: Teaching Large Language Models to Reason Complex Questions By Themselves Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose SELF-EXPLAIN to generate CoT examples by LLMs inspired by encoding specificity in human memory retrieval. |
Jiachen Zhao; Zonghai Yao; Zhichao Yang; Hong Yu; | arxiv-cs.CL | 2023-11-12 |
68 | BizBench: A Quantitative Reasoning Benchmark for Business and Finance Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce three diverse financially-themed code-generation tasks from newly collected and augmented QA data. |
RIK KONCEL-KEDZIORSKI et. al. | arxiv-cs.CL | 2023-11-11 |
69 | Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Large Multimodal Models (LMMs) have shown promise in vision-language tasks but struggle with high-resolution input and detailed scene understanding. Addressing these challenges, we introduce Monkey to enhance LMM capabilities. |
ZHANG LI et. al. | arxiv-cs.CV | 2023-11-11 |
70 | Knowledgeable Preference Alignment for LLMs in Domain-specific Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we present a novel pipeline to apply LLMs for domain-specific question answering (QA) that incorporates domain knowledge graphs (KGs), addressing an important direction of LLM application. |
YICHI ZHANG et. al. | arxiv-cs.CL | 2023-11-11 |
71 | SEMQA: Semi-Extractive Multi-Source Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we introduce a new QA task for answering multi-answer questions by summarizing multiple diverse sources in a semi-extractive fashion. |
TAL SCHUSTER et. al. | arxiv-cs.CL | 2023-11-08 |
72 | Leveraging Structured Information for Explainable Multi-hop Question Answering and Reasoning Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we investigate constructing and leveraging extracted semantic structures (graphs) for multi-hop question answering, especially the reasoning process. |
Ruosen Li; Xinya Du; | arxiv-cs.CL | 2023-11-07 |
73 | In-Context Learning for Knowledge Base Question Answering for Unmanned Systems Based on Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we focus on the CCKS2023 Competition of Question Answering with Knowledge Graph Inference for Unmanned Systems. |
Yunlong Chen; Yaming Zhang; Jianfei Yu; Li Yang; Rui Xia; | arxiv-cs.CL | 2023-11-06 |
74 | Adapting Pre-trained Generative Models for Extractive Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we introduce a novel approach that uses the power of pre-trained generative models to address extractive QA tasks by generating indexes corresponding to context tokens or sentences that form part of the answer. |
Prabir Mallick; Tapas Nayak; Indrajit Bhattacharya; | arxiv-cs.CL | 2023-11-06 |
75 | Tailoring Self-Rationalizers with Multi-Reward Distillation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we enable small-scale LMs (approx. 200x smaller than GPT-3) to generate rationales that not only improve downstream task performance, but are also more plausible, consistent, and diverse, assessed both by automatic and human evaluation. |
SAHANA RAMNATH et. al. | arxiv-cs.CL | 2023-11-05 |
76 | Divide & Conquer for Entailment-aware Multi-hop Evidence Retrieval Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we demonstrate that textual entailment relation is another important relevance dimension that should be considered. |
Fan Luo; Mihai Surdeanu; | arxiv-cs.CL | 2023-11-05 |
77 | Causal Question Answering with Reinforcement Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Hence, in this paper, we aim to answer causal questions with CauseNet, a large-scale dataset of causal relations and their provenance data. |
Lukas Blübaum; Stefan Heindorf; | arxiv-cs.AI | 2023-11-05 |
78 | ChaTA: Towards An Intelligent Question-Answer Teaching Assistant Using Open-Source LLMs Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To address the challenges of scalable and intelligent question-answering (QA), we introduce an innovative solution that leverages open-source Large Language Models (LLMs) from the LLaMA-2 family to ensure data privacy. |
Yann Hicke; Anmol Agarwal; Qianou Ma; Paul Denny; | arxiv-cs.LG | 2023-11-05 |
79 | Perturbation-based Active Learning for Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we propose a perturbation-based active learning acquisition strategy and demonstrate it is more effective than existing commonly used strategies. |
Fan Luo; Mihai Surdeanu; | arxiv-cs.CL | 2023-11-04 |
80 | Hint-enhanced In-Context Learning Wakes Large Language Models Up for Knowledge-intensive Tasks Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, under the standard ICL setting, LLMs may sometimes neglect query-related information in demonstrations, leading to incorrect predictions. To address this limitation, we propose a new paradigm called Hint-enhanced In-Context Learning (HICL) to explore the power of ICL in open-domain question answering, an important form in knowledge-intensive tasks. |
YIFAN WANG et. al. | arxiv-cs.CL | 2023-11-03 |
81 | SAC$^3$: Reliable Hallucination Detection in Black-Box Language Models Via Semantic-aware Cross-check Consistency Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: To achieve this goal, we re-examine existing detection approaches based on the self-consistency of LMs and uncover two types of hallucinations resulting from 1) question-level and 2) model-level, which cannot be effectively identified through self-consistency check alone. Building upon this discovery, we propose a novel sampling-based method, i.e., semantic-aware cross-check consistency (SAC$^3$) that expands on the principle of self-consistency checking. |
Jiaxin Zhang; Zhuohang Li; Kamalika Das; Bradley A. Malin; Sricharan Kumar; | arxiv-cs.CL | 2023-11-03 |
82 | CASE: Commonsense-Augmented Score with An Expanded Answer Space Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We propose CASE, a Commonsense-Augmented Score with an Expanded Answer Space. |
Wenkai Chen; Sahithya Ravi; Vered Shwartz; | arxiv-cs.CL | 2023-11-02 |
83 | ACQUIRED: A Dataset for Answering Counterfactual Questions In Real-Life Videos Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: It involves predicting the outcomes of hypothetical circumstances based on vision and language inputs, which enables AI models to learn from failures and explore hypothetical scenarios. |
TE-LIN WU et. al. | arxiv-cs.CV | 2023-11-02 |
84 | Predicting Question-Answering Performance of Large Language Models Through Semantic Consistency Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We address the task of assessing question-answering (QA) semantic consistency of contemporary large language models (LLMs) by manually creating a benchmark dataset with high-quality paraphrases for factual questions, and release the dataset to the community. |
Ella Rabinovich; Samuel Ackerman; Orna Raz; Eitan Farchi; Ateret Anaby-Tavor; | arxiv-cs.CL | 2023-11-02 |
85 | Long Story Short: A Summarize-then-Search Method for Long Video Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This capability has been particularly effective in settings such as narrative question answering, where the diversity of tasks is immense, but the available supervision data is small. In this work, we investigate if such language models can extend their zero-shot reasoning abilities to long multimodal narratives in multimedia content such as drama, movies, and animation, where the story plays an essential role. |
Jiwan Chung; Youngjae Yu; | arxiv-cs.CV | 2023-11-02 |
86 | From Image to Language: A Critical Analysis of Visual Question Answering (VQA) Approaches, Challenges, and Opportunities Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The work aims to navigate both beginners and experts by shedding light on the potential avenues of research and expanding the boundaries of the field. |
Md Farhan Ishmam; Md Sakib Hossain Shovon; M. F. Mridha; Nilanjan Dey; | arxiv-cs.CV | 2023-11-01 |
87 | VQA-GEN: A Visual Question Answering Benchmark for Domain Generalization Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose VQA-GEN, the first ever multi-modal benchmark dataset for distribution shift generated through a shift induced pipeline. |
Suraj Jyothi Unni; Raha Moraffah; Huan Liu; | arxiv-cs.CV | 2023-11-01 |
88 | DIVKNOWQA: Assessing The Reasoning Ability of LLMs Via Open-Domain Question Answering Over Knowledge Base and Text Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Large Language Models (LLMs) have exhibited impressive generation capabilities, but they suffer from hallucinations when solely relying on their internal knowledge, especially … |
WENTING ZHAO et. al. | arxiv-cs.CL | 2023-10-31 |
89 | BioInstruct: Instruction Tuning of Large Language Models for Biomedical Natural Language Processing Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We created the BioInstruct, comprising 25,005 instructions to instruction-tune LLMs(LLaMA 1 & 2, 7B & 13B version). |
Hieu Tran; Zhichao Yang; Zonghai Yao; Hong Yu; | arxiv-cs.CL | 2023-10-30 |
90 | Split-NER: Named Entity Recognition Via Two Question-Answering-based Classifications Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we address the NER problem by splitting it into two logical sub-tasks: (1) Span Detection which simply extracts entity mention spans irrespective of entity type; (2) Span Classification which classifies the spans into their entity types. |
Jatin Arora; Youngja Park; | arxiv-cs.CL | 2023-10-30 |
91 | Language Guided Visual Question Answering: Elevate Your Multimodal Language Model Using Knowledge-Enriched Prompts Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We propose a multimodal framework that uses language guidance (LG) in the form of rationales, image captions, scene graphs, etc to answer questions more accurately. |
Deepanway Ghosal; Navonil Majumder; Roy Ka-Wei Lee; Rada Mihalcea; Soujanya Poria; | arxiv-cs.CV | 2023-10-30 |
92 | Multimodal ChatGPT for Medical Applications: An Experimental Study of GPT-4V Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we critically evaluate the capabilities of the state-of-the-art multimodal large language model, i.e., GPT-4 with Vision (GPT-4V), on Visual Question Answering (VQA) task. |
ZHILING YAN et. al. | arxiv-cs.CV | 2023-10-29 |
93 | EHRTutor: Enhancing Patient Understanding of Discharge Instructions Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents EHRTutor, an innovative multi-component framework leveraging the Large Language Model (LLM) for patient education through conversational question-answering. |
Zihao Zhang; Zonghai Yao; Huixue Zhou; Feiyun ouyang; Hong Yu; | arxiv-cs.CL | 2023-10-29 |
94 | DCQA: Document-Level Chart Question Answering Towards Complex Reasoning and Common-Sense Understanding Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we introduce a novel task named document-level chart question answering (DCQA). |
ANRAN WU et. al. | arxiv-cs.AI | 2023-10-29 |
95 | Dynamic Task and Weight Prioritization Curriculum Learning for Multimodal Imagery Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We propose a curriculum learning strategy to enhance the performance of multimodal deep learning models. |
Huseyin Fuat Alsan; Taner Arsan; | arxiv-cs.CV | 2023-10-29 |
96 | Prompt-Engineering and Transformer-based Question Generation and Evaluation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this research, we finetuned a pretrained distilBERT model on the SQuAD question answering dataset to generate questions. |
Rubaba Amyeen; | arxiv-cs.CL | 2023-10-28 |
97 | EHRXQA: A Multi-Modal Question Answering Dataset for Electronic Health Records with Chest X-ray Images Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we introduce EHRXQA, a novel multi-modal question answering dataset combining structured EHRs and chest X-ray images. |
SEONGSU BAE et. al. | arxiv-cs.CL | 2023-10-28 |
98 | ViCLEVR: A Visual Reasoning Dataset and Hybrid Multimodal Fusion Model for Visual Question Answering in Vietnamese Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Neural models for VQA have made remarkable progress on large-scale datasets, with a primary focus on resource-rich languages like English. To address this, we introduce the ViCLEVR dataset, a pioneering collection for evaluating various visual reasoning capabilities in Vietnamese while mitigating biases. |
Khiem Vinh Tran; Hao Phu Phan; Kiet Van Nguyen; Ngan Luu Thuy Nguyen; | arxiv-cs.CL | 2023-10-27 |
99 | Detrimental Contexts in Open-Domain Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we analyze how passages can have a detrimental effect on retrieve-then-read architectures used in question answering. |
Philhoon Oh; James Thorne; | arxiv-cs.CL | 2023-10-27 |
100 | Knowledge Corpus Error in Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: This study revisits the conventional formulation of QA and introduces the concept of knowledge corpus error. |
Yejoon Lee; Philhoon Oh; James Thorne; | arxiv-cs.CL | 2023-10-27 |
101 | Davidsonian Scene Graph: Improving Reliability in Fine-grained Evaluation for Text-Image Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We identify and address several reliability challenges in existing QG/A work: (a) QG questions should respect the prompt (avoiding hallucinations, duplications, and omissions) and (b) VQA answers should be consistent (not asserting that there is no motorcycle in an image while also claiming the motorcycle is blue). We address these issues with Davidsonian Scene Graph (DSG), an empirically grounded evaluation framework inspired by formal semantics. |
JAEMIN CHO et. al. | arxiv-cs.CV | 2023-10-27 |
102 | 3D-Aware Visual Question Answering About Parts, Poses and Occlusions Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we introduce the task of 3D-aware VQA, which focuses on challenging questions that require a compositional reasoning over the 3D structure of visual scenes. |
Xingrui Wang; Wufei Ma; Zhuowan Li; Adam Kortylewski; Alan Yuille; | arxiv-cs.CV | 2023-10-27 |
103 | Incorporating Probing Signals Into Multimodal Machine Translation Via Visual Question-Answering Pairs Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: This paper presents an in-depth study of multimodal machine translation (MMT), examining the prevailing understanding that MMT systems exhibit decreased sensitivity to visual information when text inputs are complete. |
YUXIN ZUO et. al. | arxiv-cs.CL | 2023-10-26 |
104 | Improving Zero-shot Reader By Reducing Distractions from Irrelevant Documents in Open-Domain Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This study aims at the feasibility of a zero-shot reader that addresses the challenges of computational cost and the need for labeled data. |
Sukmin Cho; Jeongyeon Seo; Soyeong Jeong; Jong C. Park; | arxiv-cs.CL | 2023-10-26 |
105 | Binary State Recognition By Robots Using Visual Question Answering of Pre-Trained Vision-Language Model Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Until now, these states have been recognized by programmatically describing the state of a point cloud or raw image, by annotating and learning images, by using special sensors, etc. In contrast to these methods, we apply Visual Question Answering (VQA) from a Pre-Trained Vision-Language Model (PTVLM) trained on a large-scale dataset, to such binary state recognition. |
Kento Kawaharazuka; Yoshiki Obinata; Naoaki Kanazawa; Kei Okada; Masayuki Inaba; | arxiv-cs.RO | 2023-10-25 |
106 | Diversity Enhanced Narrative Question Generation for Storybooks Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we introduce a multi-question generation model (mQG), which is capable of generating multiple, diverse, and answerable questions by focusing on context and questions. |
Hokeun Yoon; JinYeong Bak; | arxiv-cs.CL | 2023-10-25 |
107 | Quality > Quantity: Synthetic Corpora from Foundation Models for Closed-Domain Extractive Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we study extractive question answering within closed domains and introduce the concept of targeted pre-training. |
Saptarshi Sengupta; Connor Heaton; Shreya Ghosh; Preslav Nakov; Prasenjit Mitra; | arxiv-cs.CL | 2023-10-25 |
108 | Enhancing Document Information Analysis with Multi-Task Pre-training: A Robust Approach for Information Extraction in Visually-Rich Documents Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper introduces a deep learning model tailored for document information analysis, emphasizing document classification, entity relation extraction, and document visual question answering. |
Tofik Ali; Partha Pratim Roy; | arxiv-cs.CV | 2023-10-25 |
109 | Exploring Question Decomposition for Zero-Shot VQA Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, we show that naive application of model-written decompositions can hurt performance. We introduce a model-driven selective decomposition approach for second-guessing predictions and correcting errors, and validate its effectiveness on eight VQA tasks across three domains, showing consistent improvements in accuracy, including improvements of >20% on medical VQA datasets and boosting the zero-shot performance of BLIP-2 above chance on a VQA reformulation of the challenging Winoground task. |
Zaid Khan; Vijay Kumar BG; Samuel Schulter; Manmohan Chandraker; Yun Fu; | arxiv-cs.CV | 2023-10-25 |
110 | 1-PAGER: One Pass Answer Generation and Evidence Retrieval Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present 1-Pager the first system that answers a question and retrieves evidence using a single Transformer-based model and decoding process. |
Palak Jain; Livio Baldini Soares; Tom Kwiatkowski; | arxiv-cs.CL | 2023-10-25 |
111 | Glance and Focus: Memory Prompting for Multi-Event Video Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In contrast, humans can easily tackle it by using a series of episode memory as anchors to quickly locate question-related key moments for reasoning. To mimic this effective reasoning strategy, we propose the Glance-Focus model. |
Ziyi Bai; Ruiping Wang; Xilin Chen; | nips | 2023-10-24 |
112 | BeaverTails: A Human-Preference Dataset for LLM Harmlessness Alignment Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we introduce the BeaverTails dataset, aimed at fostering research on safety alignment in large language models (LLMs). |
JIAMING JI et. al. | nips | 2023-10-24 |
113 | Large Language Models Are Temporal and Causal Reasoners for Video Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we develop LLaMA-VQA by applying Flipped-VQA to LLaMA, and it outperforms both LLMs-based and non-LLMs-based models on five challenging VideoQA benchmarks. |
Dohwan Ko; Ji Soo Lee; Wooyoung Kang; Byungseok Roh; Hyunwoo J. Kim; | arxiv-cs.CV | 2023-10-24 |
114 | Evaluating Open-QA Evaluation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We introduce a new task, QA Evaluation (QA-Eval) and the corresponding dataset EVOUNA, designed to assess the accuracy of AI-generated answers in relation to standard answers within Open-QA. |
CUNXIANG WANG et. al. | nips | 2023-10-24 |
115 | PreWoMe: Exploiting Presuppositions As Working Memory for Long Form Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we propose PreWoMe, a unified approach capable of handling any type of information-seeking question. |
Wookje Han; Jinsol Park; Kyungjae Lee; | arxiv-cs.CL | 2023-10-24 |
116 | MarkQA: A Large Scale KBQA Dataset with Numerical Reasoning Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we focus on the complex numerical reasoning in KBQA and propose a new task, NR-KBQA, which necessitates the ability to perform both multi-hop reasoning and numerical reasoning. |
Xiang Huang; Sitao Cheng; Yuheng Bao; Shanshan Huang; Yuzhong Qu; | arxiv-cs.CL | 2023-10-24 |
117 | ECG-QA: A Comprehensive Question Answering Dataset Combined With Electrocardiogram Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: This leaves the vast potential of combining electrocardiogram (ECG) data with these systems largely untapped. To address this gap, we present ECG-QA, the first QA dataset specifically designed for ECG analysis. |
Jungwoo Oh; Seongsu Bae; Gyubok Lee; Joon-myoung Kwon; Edward Choi; | nips | 2023-10-24 |
118 | Visual Cropping Improves Zero-Shot Question Answering of Multimodal Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we investigate whether multimodal LLMs can perceive small details as well as large details in images. |
Jiarui Zhang; Mahyar Khayatkhoei; Prateek Chhikara; Filip Ilievski; | arxiv-cs.CV | 2023-10-24 |
119 | 3D-Aware Visual Question Answering About Parts, Poses and Occlusions Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we introduce the task of 3D-aware VQA, which focuses on challenging questions that require a compositional reasoning over the 3D structure of visual scenes. |
Xingrui Wang; Zhuowan Li; Wufei Ma; Adam Kortylewski; Alan Yuille; | nips | 2023-10-24 |
120 | Emergent Communication in Interactive Sketch Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Vision-based emergent communication (EC) aims to learn to communicate through sketches and demystify the evolution of human communication. |
Zixing Lei; Yiming Zhang; Yuxin Xiong; Siheng Chen; | arxiv-cs.AI | 2023-10-24 |
121 | ToolQA: A Dataset for LLM Question Answering with External Tools Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: However, current evaluation methods do not distinguish between questions that can be answered using LLMs’ internal knowledge and those that require external information through tool use. To address this issue, we introduce a new dataset called ToolQA, which is designed to faithfully evaluate LLMs’ ability to use external tools for question answering. |
Yuchen Zhuang; Yue Yu; Kuan Wang; Haotian Sun; Chao Zhang; | nips | 2023-10-24 |
122 | AVIS: Autonomous Visual Information Seeking with Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose an autonomous information seeking visual question answering framework, AVIS. |
ZINIU HU et. al. | nips | 2023-10-24 |
123 | Exploring Question Decomposition for Zero-Shot VQA Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, we show that naive application of model-written decompositions can hurt performance. We introduce a model-driven _selective decomposition_ approach for second-guessing predictions and correcting errors, and validate its effectiveness on eight VQA tasks across three domains, showing consistent improvements in accuracy, including improvements of >20% on medical VQA datasets and boosting the zero-shot performance of BLIP-2 significantly above chance (+18%) on the challenging Winoground task. |
Zaid Khan; Vijay Kumar B G; Samuel Schulter; Manmohan Chandraker; Yun Fu; | nips | 2023-10-24 |
124 | RealTime QA: What’s The Answer Right Now? IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We introduce RealTime QA, a dynamic question answering (QA) platform that announces questions and evaluates systems on a regular basis (weekly in this version). |
JUNGO KASAI et. al. | nips | 2023-10-24 |
125 | Benchmarking Large Language Models on CMExam – A Comprehensive Chinese Medical Exam Dataset Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: However, evaluating LLMs in the medical field is challenging due to the lack of standardized and comprehensive datasets. To address this gap, we introduce CMExam, sourced from the Chinese National Medical Licensing Examination. |
JUNLING LIU et. al. | nips | 2023-10-24 |
126 | EHRXQA: A Multi-Modal Question Answering Dataset for Electronic Health Records with Chest X-ray Images Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we introduce EHRXQA, a novel multi-modal question answering dataset for structured EHRs and chest X-ray images. |
SEONGSU BAE et. al. | nips | 2023-10-24 |
127 | EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We introduce EgoSchema, a very long-form video question-answering dataset, and benchmark to evaluate long video understanding capabilities of modern vision and language systems. |
Karttikeya Mangalam; Raiymbek Akshulakov; Jitendra Malik; | nips | 2023-10-24 |
128 | Foundation Model Is Efficient Multimodal Multitask Model Selector Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Although recent-advanced approaches employed lightweight metrics to measure models’ transferability, they often depend heavily on the prior knowledge of a single task, making them inapplicable in a multi-modal multi-task scenario. To tackle this issue, we propose an efficient multitask model selector (EMMS), which employs large-scale foundation models to transform diverse label formats such as categories, texts, and bounding boxes of different downstream tasks into a unified noisy label embedding. |
FANQING MENG et. al. | nips | 2023-10-24 |
129 | From Parameter-Efficient to Memory-Efficient Fine-Tuning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we first investigate what is a key factor for the success of existing PEFT methods, and realize that it’s essential to preserve the PLM’s starting point when initializing a PEFT method. With this finding, we propose memory-efficient fine-tuning (MEFT) that inserts adapters into a PLM, preserving the PLM’s starting point and making it reversible without additional pre-training. |
Baohao Liao; Shaomu Tan; Christof Monz; | nips | 2023-10-24 |
130 | LoRA: A Logical Reasoning Augmented Dataset for Visual Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: VQA tasks and large vision-and-language models aim to tackle reasoning problems, but the accuracy, consistency and fabrication of the generated answers is hard to evaluate in the absence of a VQA dataset that can offer formal, comprehensive and systematic complex logical reasoning questions. To address this gap, we present LoRA, a novel Logical Reasoning Augmented VQA dataset that requires formal and complex description logic reasoning based on a food-and-kitchen knowledge base. |
Jingying Gao; Qi Wu; Alan Blair; Maurice Pagnucco; | nips | 2023-10-24 |
131 | TOA: Task-oriented Active VQA Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, they may either drop the essential visual information to answer the question correctly or involve irrelevant objects to the task-of-interest. To address this problem, we propose to let large language models make an initial hypothesis according to their knowledge, then actively collect the visual evidence required to verify the hypothesis. |
xiaoying xing; Mingfu Liang; Ying Wu; | nips | 2023-10-24 |
132 | TableQAKit: A Comprehensive and Practical Toolkit for Table-based Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper introduces TableQAKit, the first comprehensive toolkit designed specifically for TableQA. |
FANGYU LEI et. al. | arxiv-cs.CL | 2023-10-23 |
133 | Generative Pre-trained Transformer for Vietnamese Community-based COVID-19 Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce a novel approach by conducting a comparative analysis of different Transformers vs SOTA models in the community-based COVID-19 question answering dataset. |
Tam Minh Vo; Khiem Vinh Tran; | arxiv-cs.CL | 2023-10-23 |
134 | Strong and Efficient Baselines for Open Domain Conversational Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we study the State-of-the-Art (SotA) Dense Passage Retrieval (DPR) retriever and Fusion-in-Decoder (FiD) reader pipeline, and show that it significantly underperforms when applied to ODConvQA tasks due to various limitations. |
Andrei C. Coman; Gianni Barlacchi; Adrià de Gispert; | arxiv-cs.CL | 2023-10-23 |
135 | API-Assisted Code Generation for Question Answering on Varied Table Structures Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In response, this paper introduces a unified TableQA framework that: (1) provides a unified representation for structured tables as multi-index Pandas data frames, (2) uses Python as a powerful querying language, and (3) uses few-shot prompting to translate NL questions into Python programs, which are executable on Pandas data frames. |
Yihan Cao; Shuyi Chen; Ryan Liu; Zhiruo Wang; Daniel Fried; | arxiv-cs.CL | 2023-10-23 |
136 | DISC-FinLLM: A Chinese Financial Large Language Model Based on Multiple Experts Fine-tuning Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We propose Multiple Experts Fine-tuning Framework to build a financial large language model (LLM), DISC-FinLLM. |
WEI CHEN et. al. | arxiv-cs.CL | 2023-10-23 |
137 | Reference Free Domain Adaptation for Translation of Noisy Questions with Question Specific Rewards Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Creating a synthetic parallel corpus from such data is also difficult due to its noisy nature. To address this issue, we propose a training methodology that fine-tunes the NMT system only using source-side data. |
BABAN GAIN et. al. | arxiv-cs.CL | 2023-10-23 |
138 | Tree of Clarifications: Answering Ambiguous Questions with Retrieval-Augmented Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: To cope with the challenge, we propose a novel framework, Tree of Clarifications (ToC): It recursively constructs a tree of disambiguations for the AQ — via few-shot prompting leveraging external knowledge — and uses it to generate a long-form answer. |
Gangwoo Kim; Sungdong Kim; Byeongguk Jeon; Joonsuk Park; Jaewoo Kang; | arxiv-cs.CL | 2023-10-23 |
139 | QA-NatVer: Question Answering for Natural Logic-based Fact Verification Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: To this end, we propose to use question answering to predict natural logic operators, taking advantage of the generalization capabilities of instruction-tuned language models. |
Rami Aly; Marek Strong; Andreas Vlachos; | arxiv-cs.CL | 2023-10-22 |
140 | An In-Context Schema Understanding Method for Knowledge Base Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, in doing so, a great challenge for LLMs is to understand the schema of knowledge bases. Therefore, in this paper, we propose an In-Context Schema Understanding (ICSU) method for facilitating LLMs to be used as a semantic parser in KBQA. |
YANTAO LIU et. al. | arxiv-cs.CL | 2023-10-22 |
141 | Text Fact Transfer Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Text style transfer is a prominent task that aims to control the style of text without inherently changing its factual content. To cover more text modification applications, such as adapting past news for current events and repurposing educational materials, we propose the task of text fact transfer, which seeks to transfer the factual content of a source text between topics without modifying its style. |
Nishant Balepur; Jie Huang; Kevin Chen-Chuan Chang; | arxiv-cs.CL | 2023-10-22 |
142 | Diversify Question Generation with Retrieval-Augmented Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: These methods, however, have not considered the potential of external knowledge for expression diversity. To bridge this gap, we propose RAST, a framework for Retrieval-Augmented Style Transfer, where the objective is to utilize the style of diverse templates for question generation. |
QI GOU et. al. | arxiv-cs.CL | 2023-10-22 |
143 | Retrieval-Augmented Chain-of-Thought in Semi-structured Domains Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This study explores leveraging the semi-structured nature of legal and financial data to efficiently retrieve relevant context, enabling the use of LLMs for domain-specialized QA. |
Vaibhav Mavi; Abulhair Saparov; Chen Zhao; | arxiv-cs.CL | 2023-10-22 |
144 | Merging Generated and Retrieved Knowledge for Open-Domain QA Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Based on the intuition that answers supported by both sources are more likely to be correct, we propose COMBO, a Compatibility-Oriented knowledge Merging for Better Open-domain QA framework, to effectively leverage the two sources of information. |
YUNXIANG ZHANG et. al. | arxiv-cs.CL | 2023-10-22 |
145 | Large Language Models and Multimodal Retrieval for Visual Word Sense Disambiguation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Visual Word Sense Disambiguation (VWSD) is a novel challenging task with the goal of retrieving an image among a set of candidates, which better represents the meaning of an ambiguous word within a given context. In this paper, we make a substantial step towards unveiling this interesting task by applying a varying set of approaches. |
Anastasia Kritharoula; Maria Lymperaiou; Giorgos Stamou; | arxiv-cs.CL | 2023-10-21 |
146 | Self-prompted Chain-of-Thought on Large Language Models for Open-domain Multi-hop Reasoning Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we propose Self-prompted Chain-of-Thought (SP-CoT), an automated framework to mass-produce high quality CoTs of LLMs, by LLMs and for LLMs. |
Jinyuan Wang; Junlong Li; Hai Zhao; | arxiv-cs.CL | 2023-10-20 |
147 | SALMONN: Towards Generic Hearing Abilities for Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we propose SALMONN, a speech audio language music open neural network, built by integrating a pre-trained text-based large language model (LLM) with speech and audio encoders into a single multimodal model. |
CHANGLI TANG et. al. | arxiv-cs.SD | 2023-10-20 |
148 | Test-Time Self-Adaptive Small Language Models for Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we show and investigate the capabilities of smaller self-adaptive LMs, only with unlabeled test data. |
Soyeong Jeong; Jinheon Baek; Sukmin Cho; Sung Ju Hwang; Jong C. Park; | arxiv-cs.CL | 2023-10-20 |
149 | MoqaGPT : Zero-Shot Multi-modal Open-domain Question Answering with Large Language Model Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: To enable LLMs to tackle the task in a zero-shot manner, we introduce MoqaGPT, a straightforward and flexible framework. |
Le Zhang; Yihong Wu; Fengran Mo; Jian-Yun Nie; Aishwarya Agrawal; | arxiv-cs.CL | 2023-10-20 |
150 | A Simple Baseline for Knowledge-Based Visual Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Our main contribution in this paper is to propose a much simpler and readily reproducible pipeline which, in a nutshell, is based on efficient in-context learning by prompting LLaMA (1 and 2) using question-informative captions as contextual information. |
Alexandros Xenos; Themos Stafylakis; Ioannis Patras; Georgios Tzimiropoulos; | arxiv-cs.CV | 2023-10-20 |
151 | Robust Training for Conversational Question Answering Models with Reinforced Reformulation Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Models for conversational question answering (ConvQA) over knowledge graphs (KGs) are usually trained and tested on benchmarks of gold QA pairs. |
Magdalena Kaiser; Rishiraj Saha Roy; Gerhard Weikum; | arxiv-cs.CL | 2023-10-20 |
152 | Automatic Hallucination Assessment for Aligned Large Language Models Via Transferable Adversarial Attacks Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Specifically, this paper presents AutoDebug, an LLM-based framework to use prompting chaining to generate transferable adversarial attacks in the form of question-answering examples. |
Xiaodong Yu; Hao Cheng; Xiaodong Liu; Dan Roth; Jianfeng Gao; | arxiv-cs.CL | 2023-10-19 |
153 | CLIFT: Analysing Natural Distribution Shift on Question Answering Models in Clinical Domain Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: This paper introduces a new testbed CLIFT (Clinical Shift) for the clinical domain Question-answering task. |
Ankit Pal; | arxiv-cs.CL | 2023-10-19 |
154 | RSAdapter: Adapting Multimodal Models for Remote Sensing Visual Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: These approaches demand significant computational resources and time, and a considerable number of trainable parameters are introduced. To address these challenges, we introduce a novel method known as RSAdapter, which prioritizes runtime and parameter efficiency. |
Yuduo Wang; Pedram Ghamisi; | arxiv-cs.CV | 2023-10-19 |
155 | PSYCHIC: A Neuro-Symbolic Framework for Knowledge Graph Question-Answering Grounding Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We answer the KGQA over DBLP (DBLP-QUAD) task by proposing a neuro-symbolic (NS) framework based on PSYCHIC, an extractive QA model capable of identifying the query and entities related to a KG question. |
Hanna Abi Akl; | arxiv-cs.AI | 2023-10-19 |
156 | Time-Aware Representation Learning for Time-Sensitive Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: However, language models have difficulty understanding the relationships between time specifiers, such as ‘after’ and ‘before’, and numbers, since existing QA datasets do not include sufficient time expressions. To address this issue, we propose a Time-Context aware Question Answering (TCQA) framework. |
Jungbin Son; Alice Oh; | arxiv-cs.CL | 2023-10-19 |
157 | Understanding Retrieval Augmentation for Long-Form Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a study of retrieval-augmented language models (LMs) on long-form question answering. |
Hung-Ting Chen; Fangyuan Xu; Shane A. Arora; Eunsol Choi; | arxiv-cs.CL | 2023-10-18 |
158 | Evaluating The Symbol Binding Ability of Large Language Models for Multiple-Choice Questions in Vietnamese General Education Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we evaluate the ability of large language models (LLMs) to perform multiple choice symbol binding (MCSB) for multiple choice question answering (MCQA) tasks in zero-shot, one-shot, and few-shot settings. |
Duc-Vu Nguyen; Quoc-Nam Nguyen; | arxiv-cs.CL | 2023-10-18 |
159 | Open-ended Commonsense Reasoning with Unrestricted Answer Scope Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we leverage pre-trained language models to iteratively retrieve reasoning paths on the external knowledge base, which does not require task-specific supervision. |
CHEN LING et. al. | arxiv-cs.CL | 2023-10-17 |
160 | Systematic Assessment of Factual Knowledge in Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper proposes a framework to systematically assess the factual knowledge of LLMs by leveraging knowledge graphs (KGs). |
Linhao Luo; Thuy-Trang Vu; Dinh Phung; Gholamreza Haffari; | arxiv-cs.CL | 2023-10-17 |
161 | Open Information Extraction: A Review of Baseline Techniques, Approaches, and Applications Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: It briefly discusses the main approaches and the pros and cons of each method. |
Serafina Kamp; Morteza Fayazi; Zineb Benameur-El; Shuyan Yu; Ronald Dreslinski; | arxiv-cs.IR | 2023-10-17 |
162 | QADYNAMICS: Training Dynamics-Driven Synthetic QA Diagnostic for Zero-Shot Commonsense Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: However, current QA synthesis protocols may introduce noise from the CSKBs and generate ungrammatical questions and false negative options, which impede the model’s ability to generalize. To address these issues, we propose QADYNAMICS, a training dynamics-driven framework for QA diagnostics and refinement. |
HAOCHEN SHI et. al. | arxiv-cs.CL | 2023-10-17 |
163 | Adaptation with Self-Evaluation to Improve Selective Prediction in LLMs Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we propose a novel framework for adaptation with self-evaluation to improve the selective prediction performance of LLMs. |
JIEFENG CHEN et. al. | arxiv-cs.CL | 2023-10-17 |
164 | Will The Prince Get True Love’s Kiss? On The Model Sensitivity to Gender Perturbation Over Fairytale Texts Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Recent studies show that traditional fairytales are rife with harmful gender biases. To help mitigate these gender biases in fairytales, this work aims to assess learned biases of language models by evaluating their robustness against gender perturbations. |
Christina Chance; Da Yin; Dakuo Wang; Kai-Wei Chang; | arxiv-cs.CL | 2023-10-16 |
165 | UNK-VQA: A Dataset and A Probe Into Multi-modal Large Models’ Abstention Ability Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: This paper aims to bridge the research gap by contributing a comprehensive dataset, called UNK-VQA. |
Yanyang Guo; Fangkai Jiao; Zhiqi Shen; Liqiang Nie; Mohan Kankanhalli; | arxiv-cs.CV | 2023-10-16 |
166 | Intelligent Software Tooling for Improving Software Development Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: One of the main reasons behind this success is the availability of large datasets such as open-source code available through GitHub or image datasets of mobile Graphical User Interfaces (GUIs) with RICO and ReDRAW to be trained on. Therefore, the central research question my dissertation explores is: In what ways can the software development process be improved through leveraging DL techniques on the vast amounts of unstructured software engineering artifacts? |
Nathan Cooper; | arxiv-cs.SE | 2023-10-16 |
167 | Emerging Challenges in Personalized Medicine: Assessing Demographic Effects on Biomedical Question Answering Systems Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We find that irrelevant demographic information change up to 15% of the answers of a KG-grounded system and up to 23% of the answers of a text-based system, including changes that affect accuracy. |
Sagi Shaier; Kevin Bennett; Lawrence Hunter; Katharina von der Wense; | arxiv-cs.CL | 2023-10-16 |
168 | Unifying Image Processing As Visual Prompting Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, these advances have predominantly concentrated on high-level vision tasks, with less attention paid to low-level vision tasks. To address this issue, we propose a universal model for general image processing that covers image restoration, image enhancement, image feature extraction tasks, \textit{etc}. |
YIHAO LIU et. al. | arxiv-cs.CV | 2023-10-16 |
169 | A Search for Prompts: Generating Structured Answers from Contracts Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In many legal processes being able to action on the concrete implication of a legal question can be valuable to automating human review or signalling certain conditions (e.g., alerts around automatic renewal). To support such tasks, we present a form of legal question answering that seeks to return one (or more) fixed answers for a question about a contract clause. |
ADAM ROEGIEST et. al. | arxiv-cs.CV | 2023-10-16 |
170 | Progressive Evidence Refinement for Open-domain Multimodal Retrieval Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Secondly, a gap exists between the feature extraction of evidence and the question, which hinders the model from effectively extracting critical features from the evidence based on the given question. We propose a two-stage framework for evidence retrieval and question-answering to alleviate these issues. |
SHUWEN YANG et. al. | arxiv-cs.AI | 2023-10-14 |
171 | CarExpert: Leveraging Large Language Models for In-Car Conversational Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose CarExpert, an in-car retrieval-augmented conversational question-answering system leveraging LLMs for different tasks. |
MD RASHAD AL HASAN RONY et. al. | arxiv-cs.CL | 2023-10-14 |
172 | ChatKBQA: A Generate-then-Retrieve Framework for Knowledge Base Question Answering with Fine-tuned Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In the era of large language models (LLMs), we introduce ChatKBQA, a novel generate-then-retrieve KBQA framework built on fine-tuning open-source LLMs such as Llama-2, ChatGLM2 and Baichuan2. |
HAORAN LUO et. al. | arxiv-cs.CL | 2023-10-13 |
173 | Enhancing BERT-Based Visual Question Answering Through Keyword-Driven Sentence Selection Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The goal is to identify the document elements that answer a specific question posed in natural language. This paper describes the PoliTo’s approach to addressing this task, in particular, our best solution explores a text-only approach, leveraging an ad hoc sampling strategy. |
Davide Napolitano; Lorenzo Vaiani; Luca Cagliero; | arxiv-cs.CL | 2023-10-13 |
174 | MiniGPT-v2: Large Language Model As A Unified Interface for Vision-language Multi-task Learning Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Towards this objective, we introduce MiniGPT-v2, a model that can be treated as a unified interface for better handling various vision-language tasks. |
JUN CHEN et. al. | arxiv-cs.CV | 2023-10-13 |
175 | Question Answering for Electronic Health Records: A Scoping Review of Datasets and Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We searched for articles from January 1st, 2005 to September 30th, 2023 in four digital sources including Google Scholar, ACL Anthology, ACM Digital Library, and PubMed to collect relevant publications on EHR QA. |
Jayetri Bardhan; Kirk Roberts; Daisy Zhe Wang; | arxiv-cs.LG | 2023-10-12 |
176 | Understanding How to Inform Blind and Low-Vision Users About Data Privacy Through Privacy Question Answering Assistants Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We conducted an in-depth qualitative study with 21 US BLV participants to understand their data privacy risk perception and mitigation, as well as their information behaviors related to data privacy. |
YUANYUAN FENG et. al. | arxiv-cs.HC | 2023-10-12 |
177 | Mitigating Bias for Question Answering Models By Tracking Bias Influence Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we propose BMBI, an approach to mitigate the bias of multiple-choice QA models. |
MINGYU DEREK MA et. al. | arxiv-cs.CL | 2023-10-12 |
178 | From Large Language Models to Knowledge Graphs for Biomarker Discovery in Cancer Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we develop a domain KG to leverage cancer-specific biomarker discovery and interactive QA. |
MD. REZAUL KARIM et. al. | arxiv-cs.CL | 2023-10-12 |
179 | QASiNa: Religious Domain Question Answering Using Sirah Nabawiyah Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we propose the Question Answering Sirah Nabawiyah (QASiNa) dataset, a novel dataset compiled from Sirah Nabawiyah literatures in Indonesian language. |
Muhammad Razif Rizqullah; Ayu Purwarianti; Alham Fikri Aji; | arxiv-cs.CL | 2023-10-12 |
180 | Open-Set Knowledge-Based Visual Question Answering with Inference Paths Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we confront the challenge of \emph{explainable open-set} KB-VQA, where the system is required to answer questions with entities at wild and retain an explainable reasoning path. |
Jingru Gan; Xinzhe Han; Shuhui Wang; Qingming Huang; | arxiv-cs.LG | 2023-10-12 |
181 | Training Generative Question-Answering on Synthetic Data Obtained from An Instruct-tuned Model Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents a simple and cost-effective method for synthesizing data to train question-answering systems. |
Kosuke Takahashi; Takahiro Omi; Kosuke Arima; Tatsuya Ishigaki; | arxiv-cs.CL | 2023-10-12 |
182 | Low-Resource Clickbait Spoiling for Indonesian Via Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Our contributions include the construction of manually labeled clickbait spoiling corpus in Indonesian and an evaluation on using cross-lingual zero-shot question answering-based models to tackle clikcbait spoiling for low-resource language like Indonesian. |
Ni Putu Intan Maharani; Ayu Purwarianti; Alham Fikri Aji; | arxiv-cs.CL | 2023-10-12 |
183 | QACHECK: A Demonstration System for Question-Guided Multi-Hop Fact-Checking Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: However, existing fact-checking systems often lack transparency in their decision-making, making it challenging for users to comprehend their reasoning process. To address this, we propose the Question-guided Multi-hop Fact-Checking (QACHECK) system, which guides the model’s reasoning process by asking a series of questions critical for verifying a claim. |
Liangming Pan; Xinyuan Lu; Min-Yen Kan; Preslav Nakov; | arxiv-cs.CL | 2023-10-11 |
184 | Exploring The Landscape of Large Language Models In Medical Question Answering: Observations and Open Questions Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we evaluate a wide range of popular LLMs on their knowledge of medical questions in order to better understand their properties as a group. |
Karolina Korgul; Andrew M. Bean; Felix Krones; Robert McCraith; Adam Mahdi; | arxiv-cs.CL | 2023-10-11 |
185 | Framework for Question-Answering in Sanskrit Through Automated Construction of Knowledge Graphs Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we target the problem of building knowledge graphs for particular types of relationships from sa\d{m}sk\d{r}ta texts. |
Hrishikesh Terdalkar; Arnab Bhattacharya; | arxiv-cs.CL | 2023-10-11 |
186 | Mini-DALLE3: Interactive Text to Image By Prompting Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In addressing the iT2I problem, we present a simple approach that augments LLMs for iT2I with prompting techniques and off-the-shelf T2I models. |
Lai Zeqiang; Zhu Xizhou; Dai Jifeng; Qiao Yu; Wang Wenhai; | arxiv-cs.AI | 2023-10-11 |
187 | InstructRetro: Instruction Tuning Post Retrieval-Augmented Pretraining Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we introduce Retro 48B, the largest LLM pretrained with retrieval before instruction tuning. |
BOXIN WANG et. al. | arxiv-cs.CL | 2023-10-11 |
188 | Answer Candidate Type Selection: Text-to-Text Language Model for Closed Book Question Answering Meets Knowledge Graphs Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, the capacity of the models is limited and the quality decreases for questions with less popular entities. In this paper, we present a novel approach which works on top of the pre-trained Text-to-Text QA system to address this issue. |
MIKHAIL SALNIKOV et. al. | arxiv-cs.CL | 2023-10-10 |
189 | Jaeger: A Concatenation-Based Multi-Transformer VQA Model Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Although there has been encouraging progress in document-based question answering due to the utilization of large language and open-world prior models\cite{1}, several challenges persist, including prolonged response times, extended inference durations, and imprecision in matching. In order to overcome these challenges, we propose Jaegar, a concatenation-based multi-transformer VQA model. |
Jieting Long; Zewei Shi; Penghao Jiang; Yidong Gan; | arxiv-cs.CL | 2023-10-10 |
190 | SEER : A Knapsack Approach to Exemplar Selection for In-Context HybridQA Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we present Selection of ExEmplars for hybrid Reasoning (SEER), a novel method for selecting a set of exemplars that is both representative and diverse. |
Jonathan Tonglet; Manon Reusens; Philipp Borchert; Bart Baesens; | arxiv-cs.CL | 2023-10-10 |
191 | Solution for SMART-101 Challenge of ICCV Multi-modal Algorithmic Reasoning Task 2023 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we present our solution to a Multi-modal Algorithmic Reasoning Task: SMART-101 Challenge. |
XIANGYU WU et. al. | arxiv-cs.CV | 2023-10-10 |
192 | MemSum-DQA: Adapting An Efficient Long Document Extractive Summarizer for Document Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We introduce MemSum-DQA, an efficient system for document question answering (DQA) that leverages MemSum, a long document extractive summarizer. |
Nianlong Gu; Yingqiang Gao; Richard H. R. Hahnloser; | arxiv-cs.CL | 2023-10-10 |
193 | Towards Mitigating Hallucination in Large Language Models Via Self-Reflection Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Our investigation centers on the identification and comprehension of common problematic answers, with a specific emphasis on hallucination. To tackle this challenge, we present an interactive self-reflection methodology that incorporates knowledge acquisition and answer generation. |
ZIWEI JI et. al. | arxiv-cs.CL | 2023-10-09 |
194 | FireAct: Toward Language Agent Fine-tuning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we investigate and argue for the overlooked direction of fine-tuning LMs to obtain language agents. |
BAIAN CHEN et. al. | arxiv-cs.CL | 2023-10-09 |
195 | Causal Reasoning Through Two Layers of Cognition for Improving Generalization in Visual Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Besides, diverse interpretations of the input lead to various modes of answer generation, highlighting the role of causal reasoning between interpreting and answering steps in VQA. Through this lens, we propose Cognitive pathways VQA (CopVQA) improving the multimodal predictions by emphasizing causal reasoning factors. |
Trang Nguyen; Naoaki Okazaki; | arxiv-cs.AI | 2023-10-09 |
196 | Tackling Data Bias in MUSIC-AVQA: Crafting A Balanced Dataset for Unbiased Question-Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we meticulously review each question type from the original dataset, selecting those with pronounced answer biases. |
Xiulong Liu; Zhikang Dong; Peng Zhang; | arxiv-cs.CV | 2023-10-09 |
197 | Revisiting Large Language Models As Zero-shot Relation Extractors Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose the summarize-and-ask (\textsc{SumAsk}) prompting, a simple prompt recursively using LLMs to transform RE inputs to the effective question answering (QA) format. |
Guozheng Li; Peng Wang; Wenjun Ke; | arxiv-cs.AI | 2023-10-08 |
198 | MinPrompt: Graph-based Minimal Prompt Data Augmentation for Few-shot Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose to select the most informative data for fine-tuning, thereby improving the efficiency of the fine-tuning process with comparative or even better accuracy on the open-domain QA task. |
XIUSI CHEN et. al. | arxiv-cs.CL | 2023-10-08 |
199 | Retrieval-Generation Synergy Augmented Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: One is to retrieve from an external knowledge base, and the other is to utilize large language models to generate documents. |
Zhangyin Feng; Xiaocheng Feng; Dezhi Zhao; Maojin Yang; Bing Qin; | arxiv-cs.CL | 2023-10-08 |
200 | Analyzing Zero-Shot Abilities of Vision-Language Models on Video Understanding Tasks Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Therefore, the pertinent question to ask is: Can image-text models be adapted to video tasks and is there any benefit to using these models over pretraining directly on videos? In this work, we focus on this question by proposing a detailed study on the generalization abilities of image-text models when evaluated on video understanding tasks in a zero-shot setting. |
Avinash Madasu; Anahita Bhiwandiwalla; Vasudev Lal; | arxiv-cs.CV | 2023-10-07 |
201 | Analysis of The Reasoning with Redundant Information Provided Ability of Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The study designed a modified version of the grade school math 8K (GSM-8K) dataset which has several variants focusing on different attributes of redundant information. |
Wenbei Xie; | arxiv-cs.CL | 2023-10-06 |
202 | Policy-Gradient Training of Language Models for Ranking Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This reliance on heuristics stems from the fact that the contrastive loss itself is heuristic and does not directly optimize the downstream metrics of decision quality at the end of the processing pipeline. To address this issue, we introduce Neural PG-RANK, a novel training algorithm that learns to rank by instantiating a LLM as a Plackett-Luce ranking policy. |
Ge Gao; Jonathan D. Chang; Claire Cardie; Kianté Brantley; Thorsten Joachim; | arxiv-cs.CL | 2023-10-06 |
203 | Integrating UMLS Knowledge Into Large Language Models for Medical Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In our research, we develop an augmented LLM framework based on the Unified Medical Language System (UMLS), aiming to better serve the healthcare community. |
RUI YANG et. al. | arxiv-cs.CL | 2023-10-04 |
204 | Retrieval-augmented Generation to Improve Math Question-Answering: Trade-offs Between Groundedness and Human Preference Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we designed prompts that retrieve and use content from a high-quality open-source math textbook to generate responses to real student questions. |
ZACHARY LEVONIAN et. al. | arxiv-cs.CL | 2023-10-04 |
205 | Multimodal Question Answering for Unified Information Extraction Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Due to the diversity of tasks and settings, most current MIE models are task-specific and data-intensive, which limits their generalization to real-world scenarios with diverse task requirements and limited labeled data. To address these issues, we propose a novel multimodal question answering (MQA) framework to unify three MIE tasks by reformulating them into a unified span extraction and multi-choice QA pipeline. |
Yuxuan Sun; Kai Zhang; Yu Su; | arxiv-cs.CL | 2023-10-04 |
206 | Language Models As Knowledge Bases for Visual Word Sense Disambiguation Summary Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Abstract: Visual Word Sense Disambiguation (VWSD) is a novel challenging task that lies between linguistic sense disambiguation and fine-grained multimodal retrieval. The recent … |
Anastasia Kritharoula; Maria Lymperaiou; Giorgos Stamou; | arxiv-cs.CL | 2023-10-03 |
207 | Driving with LLMs: Fusing Object-Level Vector Modality for Explainable Autonomous Driving Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We introduce a unique object-level multimodal LLM architecture that merges vectorized numeric modalities with a pre-trained LLM to improve context understanding in driving situations. |
LONG CHEN et. al. | arxiv-cs.RO | 2023-10-03 |
208 | Think Before You Speak: Training Language Models With Pause Tokens Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We empirically evaluate $\textit{pause-training}$ on decoder-only models of 1B and 130M parameters with causal pretraining on C4, and on downstream tasks covering reasoning, question-answering, general understanding and fact recall. |
SACHIN GOYAL et. al. | arxiv-cs.CL | 2023-10-03 |
209 | On The Cognition of Visual Question Answering Models and Human Intelligence: A Comparative Study Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To inspect the association of VQA models to human cognition, we designed a survey to record human thinking process and analyzed VQA models by comparing the outputs and attention maps with those of humans. |
Liben Chen; Long Chen; Tian Ellison-Chen; Zhuoyuan Xu; | arxiv-cs.CV | 2023-10-03 |
210 | SelfGraphVQA: A Self-Supervised Graph Neural Network for Scene-based Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we demonstrate that despite the effectiveness of scene graphs in VQA tasks, current methods that utilize idealized annotated scene graphs struggle to generalize when using predicted scene graphs extracted from images. To address this issue, we introduce the SelfGraphVQA framework. |
Bruno Souza; Marius Aasan; Helio Pedrini; Adín Ramírez Rivera; | arxiv-cs.CV | 2023-10-03 |
211 | An Empirical Study of ChatGPT-3.5 on Question Answering and Code Maintenance Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Ever since the launch of ChatGPT in 2022, a rising concern is whether ChatGPT will replace programmers and kill jobs. Motivated by this widespread concern, we conducted an empirical study to systematically compare ChatGPT against programmers in question-answering and software-maintaining. |
MD MAHIR ASEF KABIR et. al. | arxiv-cs.SE | 2023-10-03 |
212 | Human Mobility Question Answering (Vision Paper) Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Mining human mobility data is crucial for various applications such as smart city planning, pandemic management, and personalised recommendation system. In this paper, we aim to tackle this gap and introduce a novel task, that is, human mobility question answering (MobQA). |
Hao Xue; Flora D. Salim; | arxiv-cs.CL | 2023-10-02 |
213 | Generating Explanations in Medical Question-Answering By Expectation Maximization Inference Over Evidence Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To do so, we propose a novel approach for generating natural language explanations for answers predicted by medical QA systems. |
Wei Sun; Mingxiao Li; Damien Sileo; Jesse Davis; Marie-Francine Moens; | arxiv-cs.CL | 2023-10-02 |
214 | ReAcTable: Enhancing ReAct for Table Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Nonetheless, a conspicuous gap exists in the research landscape, where there is limited exploration of how innovative foundational research, which integrates incremental reasoning with external tools in the context of LLMs, as exemplified by the ReAct paradigm, could potentially bring advantages to the TQA task. In this paper, we aim to fill this gap, by introducing ReAcTable (ReAct for Table Question Answering tasks), a framework inspired by the ReAct paradigm that is carefully enhanced to address the challenges uniquely appearing in TQA tasks such as interpreting complex data semantics, dealing with errors generated by inconsistent data and generating intricate data transformations. |
YUNJIA ZHANG et. al. | arxiv-cs.DB | 2023-10-01 |
215 | Testing The Limits of Unified Sequence to Sequence LLM Pretraining on Diverse Table Data Tasks Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To that end, we attempt at creating a shared modeling approach in the pretraining stage with encoder-decoder style LLMs that can cater to diverse tasks. We evaluate our approach that continually pretrains and finetunes different model families of T5 with data from tables and surrounding context, on these downstream tasks at different model scales. |
Soumajyoti Sarkar; Leonard Lausen; | arxiv-cs.CL | 2023-10-01 |
216 | Question-Answering Model for Schizophrenia Symptoms and Their Impact on Daily Life Using Mental Health Forums Data Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The purpose of this paper is to present a new methodology for building a medical dataset and obtain a QA model for analysis of symptoms and impact on daily life for a specific disease domain. |
Christian Internò; Eloisa Ambrosini; | arxiv-cs.LG | 2023-09-30 |
217 | Fine-grained Late-interaction Multi-modal Retrieval for Retrieval Augmented Visual Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: This paper proposes Fine-grained Late-interaction Multi-modal Retrieval (FLMR) which significantly improves knowledge retrieval in RA-VQA. |
Weizhe Lin; Jinghong Chen; Jingbiao Mei; Alexandru Coca; Bill Byrne; | arxiv-cs.CL | 2023-09-29 |
218 | Promoting Generalized Cross-lingual Question Answering in Few-resource Scenarios Via Self-knowledge Distillation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Beyond performance improvements, we offer valuable insights through comprehensive analyses and an ablation study, further substantiating the benefits and constraints of our approach. |
Casimiro Pio Carrino; Carlos Escolano; José A. R. Fonollosa; | arxiv-cs.CL | 2023-09-29 |
219 | Interpretable Long-Form Legal Question Answering with Retrieval-Augmented Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we propose an end-to-end methodology designed to generate long-form answers to any statutory law questions, utilizing a retrieve-then-read pipeline. |
Antoine Louis; Gijs van Dijck; Gerasimos Spanakis; | arxiv-cs.CL | 2023-09-29 |
220 | Toloka Visual Question Answering Benchmark Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we present Toloka Visual Question Answering, a new crowdsourced dataset allowing comparing performance of machine learning systems against human level of expertise in the grounding visual question answering task. |
Dmitry Ustalov; Nikita Pavlichenko; Sergey Koshelev; Daniil Likhobaba; Alisa Smirnova; | arxiv-cs.CV | 2023-09-28 |
221 | Spider4SPARQL: A Complex Benchmark for Evaluating Knowledge Graph Question Answering Systems Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we introduce Spider4SPARQL – a new SPARQL benchmark dataset featuring 9,693 previously existing manually generated NL questions and 4,721 unique, novel, and complex SPARQL queries of varying complexity. |
Catherine Kosten; Philippe Cudré-Mauroux; Kurt Stockinger; | arxiv-cs.CL | 2023-09-28 |
222 | Using Weak Supervision and Data Augmentation in Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we explore the roles weak supervision and data augmentation play in training deep neural network QA models. |
Chumki Basu; Himanshu Garg; Allen McIntosh; Sezai Sablak; John R. Wullert II; | arxiv-cs.CL | 2023-09-28 |
223 | VDC: Versatile Data Cleanser for Detecting Dirty Samples Via Visual-Linguistic Inconsistency Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Existing detectors only focus on detecting poisoned samples or noisy labels, that are often prone to weak generalization when dealing with dirty samples from other domains.In this paper, we find a commonality of various dirty samples is visual-linguistic inconsistency between images and associated labels. To capture the semantic inconsistency between modalities, we propose versatile data cleanser (VDC) leveraging the surpassing capabilities of multimodal large language models (MLLM) in cross-modal alignment and reasoning.It consists of three consecutive modules: the visual question generation module to generate insightful questions about the image; the visual question answering module to acquire the semantics of the visual content by answering the questions with MLLM; followed by the visual answer evaluation module to evaluate the inconsistency.Extensive experiments demonstrate its superior performance and generalization to various categories and types of dirty samples. |
Zihao Zhu; Mingda Zhang; Shaokui Wei; Bingzhe Wu; Baoyuan Wu; | arxiv-cs.CV | 2023-09-28 |
224 | Open-vocabulary Video Question Answering: A New Benchmark for Evaluating The Generalizability of Video Question Answering Models Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We hence propose a new benchmark, Open-vocabulary Video Question Answering (OVQA), to measure the generalizability of VideoQA models by considering rare and unseen answers. |
DOHWAN KO et. al. | iccv | 2023-09-27 |
225 | PromptCap: Prompt-Guided Image Captioning for VQA with GPT-3 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Generic image captions often miss visual details essential for the LM to answer visual questions correctly. To address this challenge, we propose PromptCap (Prompt-guided image Captioning), a captioning model designed to serve as a better connector between images and black-box LMs. |
YUSHI HU et. al. | iccv | 2023-09-27 |
226 | VQA-GNN: Reasoning with Multimodal Knowledge Via Graph Neural Networks for Visual Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To perform more expressive reasoning, we propose VQA-GNN, a new VQA model that performs bidirectional fusion between unstructured and structured multimodal knowledge to obtain unified knowledge representations. |
Yanan Wang; Michihiro Yasunaga; Hongyu Ren; Shinya Wada; Jure Leskovec; | iccv | 2023-09-27 |
227 | Simple Baselines for Interactive Video Retrieval with Questions and Answers Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Recently, there has been renewed interest in interactive systems to enhance retrieval, but existing approaches are complex and deliver limited gains in performance. In this work, we revisit this topic and propose several simple yet effective baselines for interactive video retrieval via question-answering. |
Kaiqu Liang; Samuel Albanie; | iccv | 2023-09-27 |
228 | VQA Therapy: Exploring Answer Differences By Visually Grounding Answers Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Given that different people can provide different answers to a visual question, we aim to better understand why with answer groundings. |
Chongyan Chen; Samreen Anjum; Danna Gurari; | iccv | 2023-09-27 |
229 | Encyclopedic VQA: Visual Questions About Detailed Properties of Fine-Grained Categories Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We propose Encyclopedic-VQA, a large scale visual question answering (VQA) dataset featuring visual questions about detailed properties of fine-grained categories and instances. |
THOMAS MENSINK et. al. | iccv | 2023-09-27 |
230 | Decouple Before Interact: Multi-Modal Prompt Learning for Continual Visual Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: On the other hand, neglecting the interactions between modalities will lead to poor performance. To tackle these challenging issues, we propose a comprehensive formulation for CL-VQA from the perspective of multi-modal vision-language fusion. |
ZI QIAN et. al. | iccv | 2023-09-27 |
231 | TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Based on this approach, we introduce TIFA v1.0, a benchmark consisting of 4K diverse text inputs and 25K questions across 12 categories (object, counting, etc.). |
YUSHI HU et. al. | iccv | 2023-09-27 |
232 | Toward Multi-Granularity Decision-Making: Explicit Visual Reasoning with Hierarchical Knowledge Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: To fill the gap, this paper makes progresses from two distinct perspectives: (1) It presents a Hierarchical Concept Graph (HCG) that discriminates and associates multi-granularity concepts with a multi-layered hierarchical structure, aligning visual observations with knowledge across different levels to alleviate data biases. |
Yifeng Zhang; Shi Chen; Qi Zhao; | iccv | 2023-09-27 |
233 | Discovering Spatio-Temporal Rationales for Video Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To tackle the challenge, we highlight the importance of identifying question-critical temporal moments and spatial objects from the vast amount of video content. Towards this, we propose a Spatio-Temporal Rationalizer (STR), a differentiable selection module that adaptively collects question-critical moments and objects using cross-modal interaction. |
Yicong Li; Junbin Xiao; Chun Feng; Xiang Wang; Tat-Seng Chua; | iccv | 2023-09-27 |
234 | Knowledge Proxy Intervention for Deconfounded Video Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To tackle the challenge that the confounder in VideoQA is unobserved and non-enumerable in general, we propose a model-agnostic framework called Knowledge Proxy Intervention (KPI), which introduces an extra knowledge proxy variable in the causal graph to cut the backdoor path and remove the confounder. |
Jiangtong Li; Li Niu; Liqing Zhang; | iccv | 2023-09-27 |
235 | MedEdit: Model Editing for Medical Question Answering with External Knowledge Bases Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Large Language Models (LLMs), although powerful in general domains, often perform poorly on domain-specific tasks like medical question answering (QA). |
YUCHENG SHI et. al. | arxiv-cs.CL | 2023-09-27 |
236 | Zero-Shot and Few-Shot Video Question Answering with Multi-Modal Prompts Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: However, adapting pretrained models on limited data presents challenges such as overfitting, catastrophic forgetting, and the cross-modal gap between vision and language. We introduce a parameter-efficient method to address these challenges, combining multimodal prompt learning and a transformer-based mapping network, while keeping the pretrained models frozen. |
Deniz Engin; Yannis Avrithis; | arxiv-cs.CV | 2023-09-27 |
237 | Variational Causal Inference Network for Explanatory Visual Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Moreover, they neglect the complex relationships among question words, visual regions, and explanation tokens. To address these issues, we propose a Variational Causal Inference Network (VCIN) that establishes the causal correlation between predicted answers and explanations, and captures cross-modal relationships to generate rational explanations. |
Dizhan Xue; Shengsheng Qian; Changsheng Xu; | iccv | 2023-09-27 |
238 | Tem-Adapter: Adapting Image-Text Pretraining for Video Question Answer Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: This motivates us to leverage the knowledge from image-based pretraining, despite the obvious gaps between image and video domains. To bridge these gaps, in this paper, we propose Tem-Adapter, which enables the learning of temporal dynamics and complex semantics by a visual Temporal Aligner and a textual Semantic Aligner. |
GUANGYI CHEN et. al. | iccv | 2023-09-27 |
239 | Question Answering Using Deep Learning in Low Resource Indian Language Marathi Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we investigate different transformer models for creating a reading comprehension-based Marathi question answering system. |
Dhiraj Amin; Sharvari Govilkar; Sagar Kulkarni; | arxiv-cs.CL | 2023-09-27 |
240 | Boosting In-Context Learning with Factual Knowledge Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we demonstrate that factual knowledge is imperative for the performance of ICL in three core facets, i.e., the inherent knowledge learned in LLMs, the factual knowledge derived from the selected in-context examples, and the knowledge biases in LLMs for output generation. |
Jianing Wang; Chengyu Wang; Chuanqi Tan; Jun Huang; Ming Gao; | arxiv-cs.CL | 2023-09-26 |
241 | Legal Question-Answering in The Indian Context: Efficacy, Challenges, and Potential of Modern AI Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Legal QA platforms bear the promise to metamorphose the manner in which legal experts engage with jurisprudential documents. In this exposition, we embark on a comparative exploration of contemporary AI frameworks, gauging their adeptness in catering to the unique demands of the Indian legal milieu, with a keen emphasis on Indian Legal Question Answering (AILQA). |
Shubham Kumar Nigam; Shubham Kumar Mishra; Ayush Kumar Mishra; Noel Shallum; Arnab Bhattacharya; | arxiv-cs.CL | 2023-09-26 |
242 | Question-Answering Approach to Evaluate Legal Summaries Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a novel legal summarization evaluation framework that utilizes GPT-4 to generate a set of question-answer pairs that cover main points and information in the reference summary. |
Huihui Xu; Kevin Ashley; | arxiv-cs.CL | 2023-09-26 |
243 | Fine-tuning and Aligning Question Answering Models for Complex Information Extraction Tasks Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work we propose an approach that uses and integrates extractive QA models for improved feature extraction of German business documents such as insurance reports or medical leaflets into a document analysis solution. |
Matthias Engelbach; Dennis Klau; Felix Scheerer; Jens Drawehn; Maximilien Kintz; | arxiv-cs.CL | 2023-09-26 |
244 | Does The most Sinfully Decadent Cake Ever Taste Good? Answering Yes/No Questions from Figurative Contexts Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we investigate the robustness of Question Answering (QA) models on figurative text. |
Geetanjali Rakshit; Jeffrey Flanigan; | arxiv-cs.CL | 2023-09-24 |
245 | Furthest Reasoning with Plan Assessment: Stable Reasoning Path with Retrieval-Augmented Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: These inaccuracies, accumulated by the iterative interaction between IR and LLM, lead to a disaster in effectiveness at the end. To overcome above barriers, in this paper, we propose a novel pipeline for MHQA called Furthest-Reasoning-with-Plan-Assessment (FuRePA), including an improved framework (Furthest Reasoning) and an attached module (Plan Assessor). |
Yin Zhu; Zhiling Luo; Gong Cheng; | arxiv-cs.CL | 2023-09-22 |
246 | HRoT: Hybrid Prompt Strategy and Retrieval of Thought for Table-Text Hybrid Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we introduce a new prompting strategy called Hybrid prompt strategy and Retrieval of Thought for TextTableQA. |
TONGXU LUO et. al. | arxiv-cs.CL | 2023-09-22 |
247 | SQUARE: Automatic Question Answering Evaluation Using Multiple Positive and Negative References Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a new evaluation metric: SQuArE (Sentence-level QUestion AnsweRing Evaluation), using multiple reference answers (combining multiple correct and incorrect references) for sentence-form QA. |
Matteo Gabburo; Siddhant Garg; Rik Koncel Kedziorski; Alessandro Moschitti; | arxiv-cs.CL | 2023-09-21 |
248 | Retrieving Supporting Evidence for Generative Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we report two simple experiments to automatically validate generated answers against a corpus. |
Siqing Huo; Negar Arabzadeh; Charles L. A. Clarke; | arxiv-cs.IR | 2023-09-20 |
249 | Knowledge Graph Question Answering for Materials Science (KGQA4MAT): Developing Natural Language Interface for Metal-Organic Frameworks Knowledge Graph (MOF-KG) Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a comprehensive benchmark dataset for Knowledge Graph Question Answering in Materials Science (KGQA4MAT), with a focus on metal-organic frameworks (MOFs). |
YUAN AN et. al. | arxiv-cs.AI | 2023-09-20 |
250 | Retrieve-Rewrite-Answer: A KG-to-Text Enhanced LLMs Framework for Knowledge Graph Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we study the KG-augmented language model approach for solving the knowledge graph question answering (KGQA) task that requires rich world knowledge. |
YIKE WU et. al. | arxiv-cs.CL | 2023-09-20 |
251 | Visual Question Answering in The Medical Domain Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we present domain-specific pre-training strategies, including a novel contrastive learning pretraining method, to mitigate the problem of small datasets for the Med-VQA task. |
Louisa Canepa; Sonit Singh; Arcot Sowmya; | arxiv-cs.CV | 2023-09-20 |
252 | Enhancing Open-Domain Table Question Answering Via Syntax- and Structure-aware Dense Retrieval Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Existing studies of open-domain table QA either directly adopt text retrieval methods or consider the table structure only in the encoding layer for table retrieval, which may cause syntactical and structural information loss during table scoring. To address this issue, we propose a syntax- and structure-aware retrieval method for the open-domain table QA task. |
Nengzheng Jin; Dongfang Li; Junying Chen; Joanna Siebert; Qingcai Chen; | arxiv-cs.CL | 2023-09-19 |
253 | Localize, Retrieve and Fuse: A Generalized Framework for Free-Form Question Answering Over Tables Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To this end, this paper proposes a generalized three-stage approach: Table-to- Graph conversion and cell localizing, external knowledge retrieval, and the fusion of table and text (called TAG-QA), to address the challenge of inferring long free-form answers in generative TableQA. |
WENTING ZHAO et. al. | arxiv-cs.CL | 2023-09-19 |
254 | Benchmarks for Pirá 2.0, A Reading Comprehension Dataset About The Ocean, The Brazilian Coast, and Climate Change Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we define six benchmarks over the Pir\’a dataset, covering closed generative question answering, machine reading comprehension, information retrieval, open question answering, answer triggering, and multiple choice question answering. |
PAULO PIROZELLI et. al. | arxiv-cs.CL | 2023-09-19 |
255 | QASnowball: An Iterative Bootstrapping Framework for High-Quality Question-Answering Data Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, obtaining sufficient data to build an effective and stable QA system still remains an open problem. For this problem, we introduce an iterative bootstrapping framework for QA data augmentation (named QASnowball), which can iteratively generate large-scale high-quality QA data based on a seed set of supervised examples. |
KUNLUN ZHU et. al. | arxiv-cs.CL | 2023-09-19 |
256 | KoBigBird-large: Transformation of Transformer for Korean Language Understanding Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This work presents KoBigBird-large, a large size of Korean BigBird that achieves state-of-the-art performance and allows long sequence processing for Korean language understanding. |
KISU YANG et. al. | arxiv-cs.CL | 2023-09-19 |
257 | Syntax Tree Constrained Graph Network for Visual Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To fill the gap, we suggested a novel Syntax Tree Constrained Graph Network (STCGN) for VQA based on entity message passing and syntax tree. |
Xiangrui Su; Qi Zhang; Chongyang Shi; Jiachang Liu; Liang Hu; | arxiv-cs.CV | 2023-09-17 |
258 | NOWJ1@ALQAC 2023: Enhancing Legal Task Performance with Classic Statistical Models and Pre-trained Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper describes the NOWJ1 Team’s approach for the Automated Legal Question Answering Competition (ALQAC) 2023, which focuses on enhancing legal task performance by integrating classical statistical models and Pre-trained Language Models (PLMs). |
TAN-MINH NGUYEN et. al. | arxiv-cs.CL | 2023-09-16 |
259 | Multimodal Multi-Hop Question Answering Through A Conversation Between Tools and Efficiently Finetuned Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We employ a tool-interacting divide-and-conquer strategy enabling large language models (LLMs) to answer complex multimodal multi-hop questions. |
Hossein Rajabzadeh; Suyuchen Wang; Hyock Ju Kwon; Bang Liu; | arxiv-cs.CL | 2023-09-16 |
260 | PDFTriage: Question Answering Over Long, Structured Documents Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: When a system has to query the document for context, this incongruity is brought to the fore, and seemingly trivial questions can trip up the QA system. To bridge this fundamental gap in handling structured documents, we propose an approach called PDFTriage that enables models to retrieve the context based on either structure or content. |
JON SAAD-FALCON et. al. | arxiv-cs.CL | 2023-09-16 |
261 | D3: Data Diversity Design for Systematic Generalization in Visual Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We present new evidence in the problem of Visual Question Answering (VQA) that reveals that the diversity of simple tasks (i.e. tasks formed by a few subtasks and concepts) plays a key role in achieving systematic generalization. |
AMIR RAHIMI et. al. | arxiv-cs.AI | 2023-09-15 |
262 | Investigating Answerability of LLMs for Long-Form Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a question-generation method from abstractive summaries and show that generating follow-up questions from summaries of long documents can create a challenging setting for LLMs to reason and infer from long contexts. |
Meghana Moorthy Bhat; Rui Meng; Ye Liu; Yingbo Zhou; Semih Yavuz; | arxiv-cs.CL | 2023-09-15 |
263 | SilverRetriever: Advancing Neural Passage Retrieval for Polish Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we present SilverRetriever, a neural retriever for Polish trained on a diverse collection of manually or weakly labeled datasets. |
Piotr Rybak; Maciej Ogrodniczuk; | arxiv-cs.CL | 2023-09-15 |
264 | CATfOOD: Counterfactual Augmented Training for Improving Out-of-Domain Performance and Calibration Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In recent years, large language models (LLMs) have shown remarkable capabilities at scale, particularly at generating text conditioned on a prompt. |
Rachneet Sachdeva; Martin Tutek; Iryna Gurevych; | arxiv-cs.CL | 2023-09-14 |
265 | Feature Engineering in Learning-to-Rank for Community Question Answering Task Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: These data are leveraged in automated CQA ranking systems where similar questions (and answers) are presented in response to the query of the user. In this work, we empirically investigate a few aspects of this domain. |
Nafis Sajid; Md Rashidul Hasan; Muhammad Ibrahim; | arxiv-cs.LG | 2023-09-14 |
266 | Evaluating The Ebb and Flow: An In-depth Analysis of Question-Answering Trends Across Diverse Platforms Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Community Question Answering (CQA) platforms steadily gain popularity as they provide users with fast responses to their queries. The swiftness of these responses is contingent on … |
Rima Hazra; Agnik Saha; Somnath Banerjee; Animesh Mukherjee; | arxiv-cs.SI | 2023-09-12 |
267 | Answering Subjective Induction Questions on Products By Summarizing Multi-sources Multi-viewpoints Knowledge Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: That is quite different from the traditional QA task, in which the answer to a factoid question is unique and can be found from a single data source. To address this new task, we propose a three-steps method. |
Yufeng Zhang; Meng-xiang Wang; Jianxing Yu; | arxiv-cs.CL | 2023-09-11 |
268 | NeCo@ALQAC 2023: Legal Domain Knowledge Acquisition for Low-Resource Languages Through Data Enrichment Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents NeCo Team’s solutions to the Vietnamese text processing tasks provided in the Automated Legal Question Answering Competition 2023 (ALQAC 2023), focusing on legal domain knowledge acquisition for low-resource languages through data enrichment. |
HAI-LONG NGUYEN et. al. | arxiv-cs.CL | 2023-09-11 |
269 | Two Is Better Than One: Answering Complex Questions By Multiple Knowledge Sources with Generalized Links Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we formulate the novel Multi-KB-QA task that leverages the full and partial links among multiple KBs to derive correct answers, a benchmark with diversified link and query types is also constructed to efficiently evaluate Multi-KB-QA performance. |
MINHAO ZHANG et. al. | arxiv-cs.CL | 2023-09-10 |
270 | Duplicate Question Retrieval and Confirmation Time Prediction in Software Communities Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To facilitate the task of the moderators, in this work, we have tackled two significant issues for the askubuntu CQA platform: (1) retrieval of duplicate questions given a new question and (2) duplicate question confirmation time prediction. |
Rima Hazra; Debanjan Saha; Amruit Sahoo; Somnath Banerjee; Animesh Mukherjee; | arxiv-cs.IR | 2023-09-10 |
271 | AGent: A Novel Pipeline for Automatically Creating Unanswerable Questions Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: However, manually annotating unanswerable questions is labor-intensive. To address this, we propose AGent, a novel pipeline that automatically creates new unanswerable questions by re-matching a question with a context that lacks the necessary information for a correct answer. |
Son Quoc Tran; Gia-Huy Do; Phong Nguyen-Thuan Do; Matt Kretchmar; Xinya Du; | arxiv-cs.CL | 2023-09-10 |
272 | Code-Style In-Context Learning for Knowledge-Based Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, current powerful LLMs have little exposure to logic forms during pre-training, resulting in a high format error rate. To solve this problem, we propose a code-style in-context learning method for KBQA, which converts the generation process of unfamiliar logical form into the more familiar code generation process for LLMs. |
Zhijie Nie; Richong Zhang; Zhongyuan Wang; Xudong Liu; | arxiv-cs.CL | 2023-09-09 |
273 | MMHQA-ICL: Multimodal In-context Learning for Hybrid Question Answering Over Text, Tables and Images Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Recently, with the rise of large language models (LLM), in-context learning (ICL) has become the most popular way to solve QA problems. We propose MMHQA-ICL framework for addressing this problems, which includes stronger heterogeneous data retriever and an image caption module. |
WEIHAO LIU et. al. | arxiv-cs.CL | 2023-09-09 |
274 | Can NLP Models ‘Identify’, ‘Distinguish’, and ‘Justify’ Questions That Don’t Have A Definitive Answer? Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Can SOTA models accurately identify such questions and provide a reasonable response? To investigate the above question, we introduce QnotA, a dataset consisting of five different categories of questions that don’t have definitive answers. |
AYUSHI AGARWAL et. al. | arxiv-cs.CL | 2023-09-08 |
275 | Introducing Forecast Utterance for Conversational Data Science Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A significant challenge for the agent in this endeavor is to accurately comprehend the user’s prediction goals and, consequently, formulate precise ML tasks. In this paper, we take a pioneering step towards this ambitious goal by introducing a new concept called Forecast Utterance and then focus on the automatic and accurate interpretation of users’ prediction goals from these utterances. |
Md Mahadi Hassan; Alex Knipper; Shubhra Kanti Karmaker; | arxiv-cs.CL | 2023-09-07 |
276 | Interpretable Visual Question Answering Via Reasoning Supervision Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, such models are likely to disregard crucial visual cues and often rely on multimodal shortcuts and inherent biases of the language modality to predict the correct answer, a phenomenon commonly referred to as lack of visual grounding. In this work, we alleviate this shortcoming through a novel architecture for visual question answering that leverages common sense reasoning as a supervisory signal. |
Maria Parelli; Dimitrios Mallis; Markos Diomataris; Vassilis Pitsikalis; | arxiv-cs.CV | 2023-09-07 |
277 | Augmenting Black-box LLMs with Medical Textbooks for Clinical Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, applying LLMs to medical domains remains challenging due to their inability to leverage domain-specific knowledge. In this study, we present the Large-scale Language Models Augmented with Medical Textbooks (LLM-AMT), which integrates authoritative medical textbooks as the cornerstone of its design, enhancing its proficiency in the specialized domain through plug-and-play modules, comprised of a Hybrid Textbook Retriever, supplemented by the Query Augmenter and the LLM Reader. |
Yubo Wang; Xueguang Ma; Wenhu Chen; | arxiv-cs.CL | 2023-09-05 |
278 | ATM: Action Temporality Modeling for Video Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce Action Temporality Modeling (ATM) for temporality reasoning via three-fold uniqueness: (1) rethinking the optical flow and realizing that optical flow is effective in capturing the long horizon temporality reasoning; (2) training the visual-text embedding by contrastive learning in an action-centric manner, leading to better action representations in both vision and text modalities; and (3) preventing the model from answering the question given the shuffled video in the fine-tuning stage, to avoid spurious correlation between appearance and motion and hence ensure faithful temporality reasoning. |
Junwen Chen; Jie Zhu; Yu Kong; | arxiv-cs.CV | 2023-09-05 |
279 | Understanding Video Scenes Through Text: Insights from Text-based Video Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The NewsVideoQA dataset contains question-answer pairs related to the text in news videos, while M4-ViteVQA comprises question-answer pairs from diverse categories like vlogging, traveling, and shopping. We provide an analysis of the formulation of these datasets on various levels, exploring the degree of visual understanding and multi-frame comprehension required for answering the questions. |
Soumya Jahagirdar; Minesh Mathew; Dimosthenis Karatzas; C. V. Jawahar; | arxiv-cs.CV | 2023-09-04 |
280 | DictaBERT: A State-of-the-Art BERT Suite for Modern Hebrew Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we describe the details of the training as well and the results on the different benchmarks. |
Shaltiel Shmidman; Avi Shmidman; Moshe Koppel; | arxiv-cs.CL | 2023-08-31 |
281 | Separate and Locate: Rethink The Text in Text-based Visual Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: The 1-D position embedding can only represent the left-right sequence relationship between words in a sentence, but not the complex spatial position relationship. To tackle these problems, we propose a novel method named Separate and Locate (SaL) that explores text contextual cues and designs spatial position embedding to construct spatial relations between OCR texts. |
Chengyang Fang; Jiangnan Li; Liang Li; Can Ma; Dayong Hu; | arxiv-cs.CV | 2023-08-30 |
282 | KGConv, A Conversational Corpus Grounded in Wikidata Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present KGConv, a large, conversational corpus of 71k conversations where each question-answer pair is grounded in a Wikidata fact. |
Quentin Brabant; Gwenole Lecorve; Lina M. Rojas-Barahona; Claire Gardent; | arxiv-cs.CL | 2023-08-29 |
283 | Hyperbolic Code Retrieval: A Novel Approach for Efficient Code Search Using Hyperbolic Space Embeddings Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, these methods often lead to computational and memory inefficiencies, posing a significant challenge to their real-world applicability. To tackle this challenge, we propose a novel approach, the Hyperbolic Code QA Matching (HyCoQA). |
XUNZHU TANG et. al. | arxiv-cs.SE | 2023-08-29 |
284 | UniPT: Universal Parallel Tuning for Transfer Learning with Efficient Parameter and Memory Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: To this end, we propose a new memory-efficient PETL strategy, dubbed Universal Parallel Tuning (UniPT). |
HAIWEN DIAO et. al. | arxiv-cs.CV | 2023-08-28 |
285 | Empowering Cross-lingual Abilities of Instruction-tuned Large Language Models By Translation-following Demonstrations Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: This disparity is demanded in further fine-tuning and affecting the cross-lingual abilities of LLMs. In this paper, we propose to empower Instructiontuned LLMs (It-LLMs) in languages other than English by building semantic alignment between them. |
Leonardo Ranaldi; Giulia Pucci; Andre Freitas; | arxiv-cs.CL | 2023-08-27 |
286 | Knowledge-Driven CoT: Exploring Faithful Reasoning in LLMs for Knowledge-intensive Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Even so, suffering from hallucinations and the inability to access external knowledge, LLMs often come with incorrect or unfaithful intermediate reasoning steps, especially in the context of answering knowledge-intensive tasks such as KBQA. To alleviate this issue, we propose a framework called Knowledge-Driven Chain-of-Thought (KD-CoT) to verify and modify reasoning traces in CoT via interaction with external knowledge, and thus overcome the hallucinations and error propagation. |
KEHENG WANG et. al. | arxiv-cs.CL | 2023-08-25 |
287 | Knowledge-Based Version Incompatibility Detection for Deep Learning Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Therefore, these techniques cannot detect version issues due to undocumented version constraints or issues involving hardware drivers or OS. To address this challenge, we propose to leverage the abundant discussions of DL version issues from Stack Overflow to facilitate version incompatibility detection. |
Zhongkai Zhao; Bonan Kou; Mohamed Yilmaz Ibrahim; Muhao Chen; Tianyi Zhang; | arxiv-cs.SE | 2023-08-25 |
288 | Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we introduce the Qwen-VL series, a set of large-scale vision-language models (LVLMs) designed to perceive and understand both texts and images. |
JINZE BAI et. al. | arxiv-cs.CV | 2023-08-24 |
289 | Answer Mining from A Pool of Images: Towards Retrieval-Based Visual Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Towards solving the RETVQA task, we propose a unified Multi Image BART (MI-BART) that takes a question and retrieved images using our relevance encoder for free-form fluent answer generation. |
Abhirama Subramanyam Penamakuri; Manish Gupta; Mithun Das Gupta; Anand Mishra; | ijcai | 2023-08-23 |
290 | FlexKBQA: A Flexible LLM-Powered Framework for Few-Shot Knowledge Base Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: To mitigate the burden associated with manual annotation, we introduce FlexKBQA by utilizing Large Language Models (LLMs) as program translators for addressing the challenges inherent in the few-shot KBQA task. |
ZHENYU LI et. al. | arxiv-cs.CL | 2023-08-23 |
291 | COOL, A Context Outlooker, and Its Application to Question Answering and Other Natural Language Processing Tasks Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present an outlook attention mechanism, COOL, for natural language processing. |
Fangyi Zhu; See-Kiong Ng; Stéphane Bressan; | ijcai | 2023-08-23 |
292 | SQuAD-SRC: A Dataset for Multi-Accent Spoken Reading Comprehension Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we construct a large-scale multi-accent human spoken dataset SQuAD-SRC, in order to study the problem of multi-accent spoken reading comprehension. |
Yixuan Tang; Anthony K.H: Tung; | ijcai | 2023-08-23 |
293 | TG-VQA: Ternary Game of Video Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we innovatively resort to game theory, which can simulate complicated relationships among multiple players with specific interaction strategies, e.g., video, question, and answer as ternary players, to achieve fine-grained alignment for VideoQA task. |
HAO LI et. al. | ijcai | 2023-08-23 |
294 | Local and Global: Temporal Question Answering Via Information Fusion Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Despite the fruitful efforts of previous models in temporal KGQA, they still have several limitations. (I) They neither emphasize the graph structural information between entities in KGs nor explicitly utilize a multi-hop relation path through graph neural networks to enhance answer prediction. (II) They adopt pre-trained language models (LMs) to obtain question representations, focusing merely on the global information related to the question while not highlighting the local information of the entities in KGs. To address these limitations, we introduce a novel model that simultaneously explores both Local information and Global information for the task of temporal KGQA (LGQA). |
YONGHAO LIU et. al. | ijcai | 2023-08-23 |
295 | A Logic-based Approach to Contrastive Explainability for Neurosymbolic Visual Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a CE framework for VQA that uses a neurosymbolic VQA architecture which disentangles perception from reasoning. |
Thomas Eiter; Tobias Geibinger; Nelson Higuera; Johannes Oetsch; | ijcai | 2023-08-23 |
296 | Keep Skills in Mind: Understanding and Implementing Skills in Commonsense Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we introduce a new approach named Dynamic Skill-aware Commonsense Question Answering (DSCQA), which transcends the limitations of traditional methods by informing the model about the need for each skill in questions and utilizes skills as a critical driver in CQA process. |
MEIKAI BAO et. al. | ijcai | 2023-08-23 |
297 | Bridging The Gap: Deciphering Tabular Data Using Large Language Model Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In the realm of natural language processing, the understanding of tabular data has perpetually stood as a focal point of scholarly inquiry. The emergence of expansive language models, exemplified by the likes of ChatGPT, has ushered in a wave of endeavors wherein researchers aim to harness these models for tasks related to table-based question answering. |
Hengyuan Zhang; Peng Chang; Zongcheng Ji; | arxiv-cs.CL | 2023-08-22 |
298 | HopPG: Self-Iterative Program Generation for Multi-Hop Question Answering Over Heterogeneous Knowledge Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: On the other hand, this way ignores the semantic information of the intermediate answers at each hop, which is beneficial for subsequent generation. To alleviate these challenges, we propose a self-iterative framework for multi-hop program generation (HopPG) over heterogeneous knowledge, which leverages the previous execution results to retrieve supporting facts and generate subsequent programs hop by hop. |
Yingyao Wang; Yongwei Zhou; Chaoqun Duan; Junwei Bao; Tiejun Zhao; | arxiv-cs.CL | 2023-08-22 |
299 | Exploring The Effectiveness of GPT Models in Test-Taking: A Case Study of The Driver’s License Knowledge Test Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Our research proposes a method that enables GPT models to answer questions by employing context from an information source not previously included in their training data. |
Saba Rahimi; Tucker Balch; Manuela Veloso; | arxiv-cs.CL | 2023-08-22 |
300 | Music Understanding LLaMA: Advancing Text-to-Music Generation with Question Answering and Captioning Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Text-to-music generation (T2M-Gen) faces a major obstacle due to the scarcity of large-scale publicly available music datasets with natural language captions. To address this, we propose the Music Understanding LLaMA (MU-LLaMA), capable of answering music-related questions and generating captions for music files. |
Shansong Liu; Atin Sakkeer Hussain; Chenshuo Sun; Ying Shan; | arxiv-cs.SD | 2023-08-22 |
301 | Knowledge Graph Prompting for Multi-Document Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, few works explore this paradigm in the scenario of multi-document question answering (MD-QA), a task demanding a thorough understanding of the logical associations among the contents and structures of different documents. To fill this crucial gap, we propose a Knowledge Graph Prompting (KGP) method to formulate the right context in prompting LLMs for MD-QA, which consists of a graph construction module and a graph traversal module. |
YU WANG et. al. | arxiv-cs.CL | 2023-08-22 |
302 | DocPrompt: Large-scale Continue Pretrain for Zero-shot and Few-shot Document Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose Docprompt for document question answering tasks with powerful zero-shot and few-shot performance. |
Sijin Wu; Dan Zhang; Teng Hu; Shikun Feng; | arxiv-cs.CL | 2023-08-21 |
303 | LibriSQA: Advancing Free-form and Open-ended Spoken Question Answering with A Novel Dataset and Framework Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Given the evident paucity of existing speech-text LLMs, we propose a lightweight, end-to-end framework to execute the SQA task on the LibriSQA, witnessing significant results. |
Zihan Zhao; Yiyang Jiang; Heyang Liu; Yanfeng Wang; Yu Wang; | arxiv-cs.CL | 2023-08-20 |
304 | Generic Attention-model Explainability By Weighted Relevance Accumulation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a weighted relevancy strategy, which takes the importance of token values into consideration, to reduce distortion when equally accumulating relevance. |
Yiming Huang; Aozhe Jia; Xiaodan Zhang; Jiawei Zhang; | arxiv-cs.CV | 2023-08-20 |
305 | Accelerated Materials Language Processing Enabled By GPT Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this study, we develop generative pretrained transformer (GPT)-enabled pipelines where the complex architectures of prior MLP models are replaced with strategic designs of prompt engineering. |
Jaewoong Choi; Byungju Lee; | arxiv-cs.CL | 2023-08-18 |
306 | PUMGPT: A Large Vision-Language Model for Product Understanding Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we focus on the product understanding task, which plays an essential role in enhancing online shopping experience. |
SHUHUI WU et. al. | arxiv-cs.CV | 2023-08-18 |
307 | Breaking Language Barriers: A Question Answering Dataset for Hindi and Marathi Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To tackle the challenge of data scarcity, we have developed a novel approach for translating the SQuAD 2.0 dataset into Hindi and Marathi. |
Maithili Sabane; Onkar Litake; Aman Chadha; | arxiv-cs.CL | 2023-08-18 |
308 | Beam Retrieval: General End-to-End Retrieval for Multi-Hop Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we introduce Beam Retrieval, a general end-to-end retrieval framework for multi-hop QA. |
Jiahao Zhang; Haiyang Zhang; Dongmei Zhang; Yong Liu; Shen Huang; | arxiv-cs.CL | 2023-08-17 |
309 | Tem-adapter: Adapting Image-Text Pretraining for Video Question Answer Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: This motivates us to leverage the knowledge from image-based pretraining, despite the obvious gaps between image and video domains. To bridge these gaps, in this paper, we propose Tem-Adapter, which enables the learning of temporal dynamics and complex semantics by a visual Temporal Aligner and a textual Semantic Aligner. |
GUANGYI CHEN et. al. | arxiv-cs.CV | 2023-08-16 |
310 | Answering Ambiguous Questions with A Database of Questions, Answers, and Revisions Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a new state-of-the-art for answering ambiguous questions that exploits a database of unambiguous questions generated from Wikipedia. |
Haitian Sun; William W. Cohen; Ruslan Salakhutdinov; | arxiv-cs.CL | 2023-08-16 |
311 | Learning The Meanings of Function Words from Grounded Language Using A Visual Question Answering Model Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Yet recent neural-network based visual question answering models apparently can learn to use function words as part of answering questions about complex visual scenes. In this paper, we study what these models learn about function words, in the hope of better understanding how the meanings of these words can be learnt by both models and children. |
Eva Portelance; Michael C. Frank; Dan Jurafsky; | arxiv-cs.CL | 2023-08-16 |
312 | DiagGPT: An LLM-based Chatbot with Automatic Topic Management for Task-Oriented Dialogue Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we introduce DiagGPT (Dialogue in Diagnosis GPT), an innovative method that extends LLMs to TOD scenarios. |
Lang Cao; | arxiv-cs.CL | 2023-08-15 |
313 | An Ensemble Approach to Question Classification: Integrating Electra Transformer, GloVe, and LSTM Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This study presents an innovative ensemble approach for question classification, combining the strengths of Electra, GloVe, and LSTM models. |
Sanad Aburass; Osama Dorgham; Maha Abu Rumman; | arxiv-cs.CL | 2023-08-13 |
314 | Performance Prediction for Multi-hop Questions Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The problem is challenging due to the multi-step nature of the retrieval process, potential dependency of the steps and the reasoning involved. To tackle this challenge, we propose multHP, a novel pre-retrieval method for predicting the performance of open-domain multi-hop questions. |
Mohammadreza Samadi; Davood Rafiei; | arxiv-cs.CL | 2023-08-11 |
315 | LittleMu: Deploying An Online Virtual Teaching Assistant Via Heterogeneous Sources Integration and Chain of Teach Prompts Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we present a virtual MOOC teaching assistant, LittleMu with minimum labeled training data, to provide question answering and chit-chat services. |
SHANGQING TU et. al. | arxiv-cs.CL | 2023-08-11 |
316 | Progressive Spatio-temporal Perception for Audio-Visual Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we propose a Progressive Spatio-Temporal Perception Network (PSTP-Net), which contains three modules that progressively identify key spatio-temporal regions w.r.t. questions. |
Guangyao Li; Wenxuan Hou; Di Hu; | arxiv-cs.CV | 2023-08-10 |
317 | Answering Unseen Questions With Smaller Language Models Using Rationale Generation and Dense Retrieval Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: When provided with sufficient explanatory context, smaller Language Models have been shown to exhibit strong reasoning ability on challenging short-answer question-answering tasks where the questions are unseen in training. We evaluate two methods for further improvement in this setting. |
Tim Hartill; Diana Benavides-Prado; Michael Witbrock; Patricia J. Riddle; | arxiv-cs.CL | 2023-08-09 |
318 | Building Interpretable and Reliable Open Information Retriever for New Domains Overnight Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we propose an information retrieval pipeline that uses entity/event linking model and query decomposition model to focus more accurately on different information units of the query. |
Xiaodong Yu; Ben Zhou; Dan Roth; | arxiv-cs.CL | 2023-08-09 |
319 | ADMUS: A Progressive Question Answering Framework Adaptable to Multiple Knowledge Sources Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Therefore, we present ADMUS, a progressive knowledge base question answering framework designed to accommodate a wide variety of datasets, including multiple languages, diverse backbone knowledge bases, and disparate question answering datasets. To accomplish the purpose, we decouple the architecture of conventional KBQA systems and propose this dataset-independent framework. |
Yirui Zhan; Yanzeng Li; Minhao Zhang; Lei Zou; | arxiv-cs.CL | 2023-08-09 |
320 | Sci-CoT: Leveraging Large Language Models for Enhanced Knowledge Distillation in Small Models for Scientific QA Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we investigate the possibility of transferring the reasoning capabilities of LLMs to smaller models via knowledge distillation. |
Yuhan Ma; Haiqi Jiang; Chenyou Fan; | arxiv-cs.CL | 2023-08-08 |
321 | On Monotonic Aggregation for Open-domain QA Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We identify the cause, and based on that we propose Judge-Specialist framework. |
Sang-eun Han; Yeonseok Jeong; Seung-won Hwang; Kyungjae Lee; | arxiv-cs.CL | 2023-08-08 |
322 | Towards An AI to Win Ghana’s National Science and Maths Quiz Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: That is the question we seek to answer in the NSMQ AI project, an open-source project that is building AI to compete live in the NSMQ and win. |
GEORGE BOATENG et. al. | arxiv-cs.HC | 2023-08-08 |
323 | Top K Relevant Passage Retrieval for Biomedical Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we work on the existing DPR framework for the biomedical domain and retrieve answers from the Pubmed articles which is a reliable source to answer medical questions. |
Shashank Gupta; | arxiv-cs.CL | 2023-08-08 |
324 | SciGraphQA: A Large-Scale Synthetic Multi-Turn Question-Answering Dataset for Scientific Graphs Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we present SciGraphQA, a synthetic multi-turn question-answer dataset related to academic graphs. |
Shengzhi Li; Nima Tajbakhsh; | arxiv-cs.CL | 2023-08-07 |
325 | KITLM: Domain-Specific Knowledge InTegration Into Language Models for Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: To boost the domain-specific understanding, we propose, KITLM, a novel knowledge base integration approach into language model through relevant information infusion. |
Ankush Agarwal; Sakharam Gawade; Amar Prakash Azad; Pushpak Bhattacharyya; | arxiv-cs.CL | 2023-08-07 |
326 | Trusting Language Models in Education Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In our work, we propose to use an XGBoost on top of BERT to output the corrected probabilities, using features based on the attention mechanism. |
JOGI SUDA NETO et. al. | arxiv-cs.CL | 2023-08-07 |
327 | Prompt Guided Copy Mechanism for Conversational Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a pluggable approach for extractive methods that introduces a novel prompt-guided copy mechanism to improve the fluency and appropriateness of the extracted answers. |
YONG ZHANG et. al. | arxiv-cs.CL | 2023-08-07 |
328 | Redundancy-aware Transformer for Video Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To this end, we propose a novel transformer-based architecture, that aims to model VideoQA in a redundancy-aware manner. |
YICONG LI et. al. | arxiv-cs.CV | 2023-08-06 |
329 | PaniniQA: Enhancing Patient Education Through Interactive Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we present PaniniQA, a patient-centric interactive question answering system designed to help patients understand their discharge instructions. |
PENGSHAN CAI et. al. | arxiv-cs.CL | 2023-08-06 |
330 | A Criterion for Artificial General Intelligence: Hypothetic-deductive Reasoning, Tested on ChatGPT Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: An elementary proxy of hypothetic-deductive reasoning is causal reasoning. We propose simple tests for both types of reasoning, and apply them to ChatGPT. |
Louis Vervoort; Vitaliy Mizyakov; Anastasia Ugleva; | arxiv-cs.AI | 2023-08-05 |
331 | Decision Knowledge Graphs: Construction of and Usage in Question Answering for Clinical Practice Guidelines Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we present a Decision Knowledge Graph (DKG) representation to store CPGs and to perform question-answering on CPGs. |
Vasudhan Varma Kandula; Pushpak Bhattacharyya; | arxiv-cs.IR | 2023-08-05 |
332 | Learning to Select The Relevant History Turns in Conversational Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Irrelevant context, on the other hand, brings noise to the system, thereby resulting in a decline in the model’s performance. In this paper, we propose a framework, DHS-ConvQA (Dynamic History Selection in Conversational Question Answering), that first generates the context and question entities for all the history turns, which are then pruned on the basis of similarity they share in common with the question at hand. |
MUNAZZA ZAIB et. al. | arxiv-cs.CL | 2023-08-04 |
333 | WebGLM: Towards An Efficient Web-Enhanced Question Answering System with Human Preferences IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We present WebGLM, a web-enhanced question-answering system based on the General Language Model (GLM). |
XIAO LIU et. al. | kdd | 2023-08-04 |
334 | Expert Knowledge-Aware Image Difference Graph Representation Learning for Difference-Aware Medical Visual Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: To contribute to automating the medical vision-language model, we propose a novel Chest-Xray Different Visual Question Answering (VQA) task. |
XINYUE HU et. al. | kdd | 2023-08-04 |
335 | RealCQA: Scientific Chart Question Answering As A Test-bed for First-Order Logic Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We present a comprehensive study of chart visual question-answering(QA) task, to address the challenges faced in comprehending and extracting data from chart visualizations within documents. |
Saleem Ahmed; Bhavin Jawade; Shubham Pandey; Srirangaraj Setlur; Venu Govindaraju; | arxiv-cs.CV | 2023-08-03 |
336 | The All-Seeing Project: Towards Panoptic Visual Recognition and Understanding of The Open World Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We present the All-Seeing (AS) project: a large-scale data and model for recognizing and understanding everything in the open world. |
WEIYUN WANG et. al. | arxiv-cs.CV | 2023-08-03 |
337 | Teaching Smaller Language Models To Generalise To Unseen Compositional Questions Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: To do so we propose a combination of multitask supervised pretraining on up to 93 tasks designed to instill diverse reasoning abilities, and a dense retrieval system that aims to retrieve a set of evidential paragraph fragments. |
Tim Hartill; Neset Tan; Michael Witbrock; Patricia J. Riddle; | arxiv-cs.CL | 2023-08-02 |
338 | SelfCheck: Using LLMs to Zero-Shot Check Their Own Step-by-Step Reasoning IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: To this end, we propose SelfCheck, a general-purpose zero-shot verification schema for recognizing such errors. |
Ning Miao; Yee Whye Teh; Tom Rainforth; | arxiv-cs.AI | 2023-08-01 |
339 | Designing A Communication Bridge Between Communities: Participatory Design for A Question-Answering AI Agent Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: How do we design an AI system that is intended to act as a communication bridge between two user communities with different mental models and vocabularies? |
Jeonghyun Lee; Vrinda Nandan; Harshvardhan Sikka; Spencer Rugaber; Ashok Gole; | arxiv-cs.HC | 2023-08-01 |
340 | Olio: A Semantic Search Interface for Data Repositories Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: For example, searching for a flight status or a game score returns a dynamically generated response along with supporting, pre-authored documents contextually relevant to the query. In this paper, we extend this hybrid search paradigm to data repositories that contain curated data sources and visualization content. |
Vidya Setlur; Andriy Kanyuka; Arjun Srinivasan; | arxiv-cs.HC | 2023-07-31 |
341 | AMOE: A Tool to Automatically Extract and Assess Organizational Evidence for Continuous Cloud Audit Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose an approach to facilitate the automatic assessment of organizational evidence, such as that extracted from security policy documents. |
Franz Deimling; Michela Fazzolari; | arxiv-cs.CR | 2023-07-31 |
342 | KoBBQ: Korean Bias Benchmark for Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we devise a process to construct a non-English bias benchmark dataset by leveraging the English BBQ dataset in a culturally adaptive way and present the KoBBQ dataset for evaluating biases in Question Answering (QA) tasks in Korean. |
JIHO JIN et. al. | arxiv-cs.CL | 2023-07-31 |
343 | Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we investigate the performance of instruction-following models across three information-seeking QA tasks. |
Vaibhav Adlakha; Parishad BehnamGhader; Xing Han Lu; Nicholas Meade; Siva Reddy; | arxiv-cs.CL | 2023-07-31 |
344 | No That’s Not What I Meant: Handling Third Position Repair in Conversational Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: For stand-alone TPR execution, we perform both automatic and human evaluations on a fine-tuned T5 model, as well as OpenAI’s GPT-3 LLMs. |
Vevake Balaraman; Arash Eshghi; Ioannis Konstas; Ioannis Papaioannou; | arxiv-cs.CL | 2023-07-31 |
345 | Question Answering with Deep Neural Networks for Semi-Structured Heterogeneous Genealogical Knowledge Graphs Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Moreover, these supervised DNN models require training datasets that are absent in the genealogical domain. This study proposes an end-to-end approach for question answering using genealogical family trees by: 1) representing genealogical data as knowledge graphs, 2) converting them to texts, 3) combining them with unstructured texts, and 4) training a trans-former-based question answering model. |
Omri Suissa; Maayan Zhitomirsky-Geffet; Avshalom Elmalech; | arxiv-cs.CL | 2023-07-30 |
346 | Around The GLOBE: Numerical Aggregation Question-Answering on Heterogeneous Genealogical Knowledge Graphs with Deep Neural Networks Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Numerical aggregation QA is critical for distant reading and analysis for researchers (and the general public) interested in investigating cultural heritage domains. Therefore, in this study, we present a new end-to-end methodology for numerical aggregation QA for genealogical trees that includes: 1) an automatic method for training dataset generation; 2) a transformer-based table selection method, and 3) an optimized transformer-based numerical aggregation QA model. |
Omri Suissa; Maayan Zhitomirsky-Geffet; Avshalom Elmalech; | arxiv-cs.CL | 2023-07-30 |
347 | BARTPhoBEiT: Pre-trained Sequence-to-Sequence and Image Transformers Models for Vietnamese Visual Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, there is a lack of models that target specific countries such as Vietnam. To address this limitation, we introduce a transformer-based Vietnamese model named BARTPhoBEiT. |
Khiem Vinh Tran; Kiet Van Nguyen; Ngan Luu Thuy Nguyen; | arxiv-cs.CL | 2023-07-28 |
348 | Context-VQA: Towards Context-Aware and Purposeful Visual Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: To further motivate and analyze the distinction between different contexts, we introduce Context-VQA, a VQA dataset that pairs images with contexts, specifically types of websites (e.g., a shopping website). |
Nandita Naik; Christopher Potts; Elisa Kreiss; | arxiv-cs.CL | 2023-07-28 |
349 | LOIS: Looking Out of Instance Semantics for Visual Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To this end, we propose a finer model framework without bounding boxes in this work, termed Looking Out of Instance Semantics (LOIS) to tackle this important issue. |
SIYU ZHANG et. al. | arxiv-cs.CV | 2023-07-26 |
350 | Keyword-Aware Relative Spatio-Temporal Graph Networks for Video Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a Keyword-aware Relative Spatio-Temporal (KRST) graph network for VideoQA. |
YI CHENG et. al. | arxiv-cs.CV | 2023-07-25 |
351 | Learning to Ask Questions for Zero-shot Dialogue State Tracking Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a method for performing zero-shot Dialogue State Tracking (DST) by casting the task as a learning-to-ask-questions framework. |
Diogo Tavares; David Semedo; Alexander Rudnicky; Joao Magalhaes; | sigir | 2023-07-25 |
352 | One Stop Shop for Question-Answering Dataset Selection Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we offer a new visualization tool — Dataset Statistical View (DSV), to lower the barrier of research entry by providing easy access to the question-answering (QA) datasets that researchers can build their work upon. |
Chang Nian Chuy; Qinmin Vivian Hu; Chen Ding; | sigir | 2023-07-25 |
353 | Explainable Conversational Question Answering Over Heterogeneous Sources Via Iterative Graph Neural Networks Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Our method EXPLAIGNN overcomes these limitations by integrating information from a mixture of sources with user-comprehensible explanations for answers. |
Philipp Christmann; Rishiraj Saha Roy; Gerhard Weikum; | sigir | 2023-07-25 |
354 | MAMO: Fine-Grained Vision-Language Representations Learning with Masked Multimodal Modeling Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a jointly masked multimodal modeling method to learn fine-grained multimodal representations. |
ZIJIA ZHAO et. al. | sigir | 2023-07-25 |
355 | A Symmetric Dual Encoding Dense Retrieval Framework for Knowledge-Intensive Visual Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: This paper presents a new pipeline for KI-VQA tasks, consisting of a retriever and a reader. |
Alireza Salemi; Juan Altmayer Pizzorno; Hamed Zamani; | sigir | 2023-07-25 |
356 | On Answer Position Bias in Transformers for Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we analyze the self-attention and embedding generation components of five Transformer-based models with different architectures and position embedding strategies. |
Rafael Glater; Rodrygo L. T. Santos; | sigir | 2023-07-25 |
357 | DocGraphLM: Documental Graph Language Model for Information Extraction Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we introduce DocGraphLM, a novel framework that combines pre-trained language models with graph semantics. |
Dongsheng Wang; Zhiqiang Ma; Armineh Nourbakhsh; Kang Gu; Sameena Shah; | sigir | 2023-07-25 |
358 | MythQA: Query-Based Large-Scale Check-Worthy Claim Detection Through Multi-Answer Open-Domain Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Many efforts have been put into how to identify check-worthy claims from a small scale of pre-collected claims, but how to efficiently detect check-worthy claims directly from a large-scale information source, such as Twitter, remains underexplored. To fill this gap, we introduce MythQA, a new multi-answer open-domain question answering(QA) task that involves contradictory stance mining for query-based large-scale check-worthy claim detection. |
Yang Bai; Anthony Colas; Daisy Zhe Wang; | sigir | 2023-07-25 |
359 | Leader-Generator Net: Dividing Skill and Implicitness for Conquering FairytaleQA Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To this end, a simple but effective Leader-Generator Network is proposed to explicitly separate and extract fine-grained reading skills and the implicitness or explicitness of the question. |
Wei Peng; Wanshui Li; Yue Hu; | sigir | 2023-07-25 |
360 | DICE: A Dataset of Italian Crime Event News Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The contribution of the paper are: (1) the creation of a corpus of 10,395 crime news; (2) the annotation schema; (3) a dataset of 10,395 news with automatic annotations; (4) a preliminary manual annotation using the proposed schema of 1000 documents. |
Giovanni Bonisoli; Maria Pia Di Buono; Laura Po; Federica Rollo; | sigir | 2023-07-25 |
361 | BeamQA: Multi-hop Knowledge Graph Question Answering with Sequence-to-Sequence Prediction and Beam Search Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, existing KGQA frameworks that use such techniques often depend on learning a transformation from the query representation to the graph embedding space, which requires access to a large training dataset. We present BeamQA, an approach that overcomes these limitations by combining a sequence-to-sequence prediction model with beam search execution in the embedding space. |
Farah Atif; Ola El Khatib; Djellel Difallah; | sigir | 2023-07-25 |
362 | GPT-3 Models Are Few-Shot Financial Reasoners Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We run several experiments with GPT-3 and find that a separate retrieval model and logic engine continue to be essential components to achieving SOTA performance in this task, particularly due to the precise nature of financial questions and the complex information stored in financial documents. With this understanding, our refined prompt-engineering approach on GPT-3 achieves near SOTA accuracy without any fine-tuning. |
Raul Salles de Padua; Imran Qureshi; Mustafa U. Karakaplan; | arxiv-cs.CL | 2023-07-25 |
363 | Analyzing Chain-of-Thought Prompting in Large Language Models Via Gradient-based Feature Attributions Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: While understanding why CoT prompting is effective is crucial to ensuring that this phenomenon is a consequence of desired model behavior, little work has addressed this; nonetheless, such an understanding is a critical prerequisite for responsible model deployment. We address this question by leveraging gradient-based feature attribution methods which produce saliency scores that capture the influence of input tokens on model output. |
Skyler Wu; Eric Meng Shen; Charumathi Badrinath; Jiaqi Ma; Himabindu Lakkaraju; | arxiv-cs.CL | 2023-07-25 |
364 | Limitations of Open-Domain Question Answering Benchmarks for Document-level Reasoning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, this approach ignores important document-level cues that can be crucial in answering questions. This paper reviews three open-domain QA benchmarks from a document-level perspective and finds that they are biased towards passage-level information. |
Ehsan Kamalloo; Charles L. A. Clarke; Davood Rafiei; | sigir | 2023-07-25 |
365 | MA-MRC: A Multi-answer Machine Reading Comprehension Dataset Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we aim to construct an MRC dataset with both data of single answer and multiple answers. |
ZHIANG YUE et. al. | sigir | 2023-07-25 |
366 | Contributions to The Improvement of Question Answering Systems in The Biomedical Domain Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: QA aims at providing inquirers with direct, short and precise answers to their natural language questions. In this Ph.D. thesis, we propose four contributions to improve the performance of QA in the biomedical domain. |
Mourad Sarrouti; | arxiv-cs.CL | 2023-07-25 |
367 | LAPCA: Language-Agnostic Pretraining with Cross-Lingual Alignment Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: While previous works used machine translation and iterative training, we present a novel approach to cross-lingual pretraining called LAPCA (language-agnostic pretraining with cross-lingual alignment). We train the LAPCA-LM model based on XLM-RoBERTa and łexa that significantly improves cross-lingual knowledge transfer for question answering and sentence retrieval on, e.g., XOR-TyDi and Mr. TyDi datasets, and in the zero-shot cross-lingual scenario performs on par with supervised methods, outperforming many of them on MKQA. |
Dmitry Abulkhanov; Nikita Sorokin; Sergey Nikolenko; Valentin Malykh; | sigir | 2023-07-25 |
368 | Cross-Market Product-Related Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We conduct a data analysis to understand the scope of the cross-market question-answering task. |
NEGIN GHASEMI et. al. | sigir | 2023-07-25 |
369 | A Zero-shot and Few-shot Study of Instruction-Finetuned Large Language Models Applied to Clinical and Biomedical Tasks Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We evaluate four state-of-the-art instruction-tuned large language models (LLMs) — ChatGPT, Flan-T5 UL2, Tk-Instruct, and Alpaca — on a set of 13 real-world clinical and biomedical natural language processing (NLP) tasks in English, such as named-entity recognition (NER), question-answering (QA), relation extraction (RE), etc. |
Yanis Labrak; Mickael Rouvier; Richard Dufour; | arxiv-cs.CL | 2023-07-22 |
370 | Robust Visual Question Answering: Datasets, Methods, and Future Challenges Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In recent years, various datasets and debiasing methods have been proposed to evaluate and enhance the VQA robustness, respectively. |
JIE MA et. al. | arxiv-cs.CV | 2023-07-21 |
371 | Towards Ontologically Grounded and Language-Agnostic Knowledge Graphs Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: What we suggest here is that by a reification of abstract objects and by acknowledging the ontological distinction between concepts and types, we arrive at an ontologically grounded and language-agnostic representation that can alleviate the difficulties in KG integration. |
Walid S. Saba; | arxiv-cs.AI | 2023-07-20 |
372 | Generator-Retriever-Generator: A Novel Approach to Open-domain Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We propose a novel approach called Generator-Retriever-Generator (GRG) that combines document retrieval techniques with a large language model (LLM), by first prompting the model to generate contextual documents based on a given question. |
Abdelrahman Abdallah; Adam Jatowt; | arxiv-cs.CL | 2023-07-20 |
373 | Investigating The Factual Knowledge Boundary of Large Language Models with Retrieval Augmentation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this study, we present an initial analysis of the factual knowledge boundaries of LLMs and how retrieval augmentation affects LLMs on open-domain QA. |
RUIYANG REN et. al. | arxiv-cs.CL | 2023-07-20 |
374 | Explaining Autonomous Driving Actions with Visual Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: To facilitate interpretability of decision-making in autonomous driving, we present a Visual Question Answering (VQA) framework, which explains driving actions with question-answering-based causal reasoning. |
Shahin Atakishiyev; Mohammad Salameh; Housam Babiker; Randy Goebel; | arxiv-cs.CV | 2023-07-19 |
375 | Towards A Performance Analysis on Pre-trained Visual Question Answering Models for Autonomous Driving Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: This short paper presents a preliminary analysis of three popular Visual Question Answering (VQA) models, namely ViLBERT, ViLT, and LXMERT, in the context of answering questions relating to driving scenarios. |
Kaavya Rekanar; Ciarán Eising; Ganesh Sistu; Martin Hayes; | arxiv-cs.CV | 2023-07-18 |
376 | Does Circuit Analysis Interpretability Scale? Evidence from Multiple Choice Capabilities in Chinchilla Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, existing analyses are done in small models far from the state of the art. To address this, we present a case study of circuit analysis in the 70B Chinchilla model, aiming to test the scalability of circuit analysis. |
TOM LIEBERUM et. al. | arxiv-cs.LG | 2023-07-18 |
377 | Traffic-Domain Video Question Answering with Automatic Captioning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we present a novel approach termed Traffic-domain Video Question Answering with Automatic Captioning (TRIVIA), which serves as a weak-supervision technique for infusing traffic-domain knowledge into large video-language models. |
Ehsan Qasemi; Jonathan M. Francis; Alessandro Oltramari; | arxiv-cs.CV | 2023-07-18 |
378 | PAT: Parallel Attention Transformer for Visual Question Answering in Vietnamese Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present in this paper a novel scheme for multimodal learning named the Parallel Attention mechanism. |
Nghia Hieu Nguyen; Kiet Van Nguyen; | arxiv-cs.CL | 2023-07-17 |
379 | Question Decomposition Improves The Faithfulness of Model-Generated Reasoning IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: As large language models (LLMs) perform more difficult tasks, it becomes harder to verify the correctness and safety of their behavior. |
ANSH RADHAKRISHNAN et. al. | arxiv-cs.CL | 2023-07-16 |
380 | DecompEval: Evaluating Generated Texts As Unsupervised Decomposed Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Furthermore, existing metrics only provide an evaluation score for each dimension without revealing the evidence to interpret how this score is obtained. To deal with these challenges, we propose a simple yet effective metric called DecompEval. |
PEI KE et. al. | arxiv-cs.CL | 2023-07-13 |
381 | Prompt Generate Train (PGT): Few-shot Domain Adaption of Retrieval Augmented Generation Models for Open Book Question-Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a framework – Prompt, Generate, Train (PGT) – to efficiently develop a generative question-answering model for open-book question-answering over a proprietary collection of text documents. |
C. S. Krishna; | arxiv-cs.LG | 2023-07-12 |
382 | Masked Vision and Language Pre-training with Unimodal and Multimodal Contrastive Losses for Medical Visual Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we present a novel self-supervised approach that learns unimodal and multimodal feature representations of input images and text using medical image caption datasets, by leveraging both unimodal and multimodal contrastive losses, along with masked language modeling and image text matching as pretraining objectives. |
Pengfei Li; Gang Liu; Jinlong He; Zixu Zhao; Shenjun Zhong; | arxiv-cs.CV | 2023-07-11 |
383 | CAT-ViL: Co-Attention Gated Vision-Language Embedding for Visual Question Localized-Answering in Robotic Surgery Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We propose an end-to-end Transformer with the Co-Attention gaTed Vision-Language (CAT-ViL) embedding for VQLA in surgical scenarios, which does not require feature extraction through detection models. |
Long Bai; Mobarakol Islam; Hongliang Ren; | arxiv-cs.CV | 2023-07-11 |
384 | Overview of BioASQ 2023: The Eleventh BioASQ Challenge on Large-Scale Biomedical Semantic Indexing and Question Answering Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: This is an overview of the eleventh edition of the BioASQ challenge in the context of the Conference and Labs of the Evaluation Forum (CLEF) 2023. BioASQ is a series of … |
ANASTASIOS NENTIDIS et. al. | arxiv-cs.CL | 2023-07-11 |
385 | Generative Pretraining in Multimodality IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We present Emu, a Transformer-based multimodal foundation model, which can seamlessly generate images and texts in multimodal context. |
QUAN SUN et. al. | arxiv-cs.CV | 2023-07-11 |
386 | BeaverTails: Towards Improved Safety Alignment of LLM Via A Human-Preference Dataset IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we introduce the BeaverTails dataset, aimed at fostering research on safety alignment in large language models (LLMs). |
JIAMING JI et. al. | arxiv-cs.CL | 2023-07-10 |
387 | SAS Video-QA: Self-Adaptive Sampling for Efficient Video Question-Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: The source codes pertaining to the method proposed in this paper are publicly available at https://github.com/declare-lab/sas-vqa. |
Wei Han; Hui Chen; Min-Yen Kan; Soujanya Poria; | arxiv-cs.CV | 2023-07-09 |
388 | XPQA: Cross-Lingual Product Question Answering in 12 Languages Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: While existing work on PQA focuses mainly on English, in practice there is need to support multiple customer languages while leveraging product information available in English. To study this practical industrial task, we present xPQA, a large-scale annotated cross-lingual PQA dataset in 12 languages, and report results in (1) candidate ranking, to select the best English candidate containing the information to answer a non-English question; and (2) answer generation, to generate a natural-sounding non-English answer based on the selected English candidate. |
Xiaoyu Shen; Akari Asai; Bill Byrne; Adria De Gispert; | acl | 2023-07-08 |
389 | DisentQA: Disentangling Parametric and Contextual Knowledge with Counterfactual Question Answering IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we propose a new paradigm in which QA models are trained to disentangle the two sources of knowledge. |
ELLA NEEMAN et. al. | acl | 2023-07-08 |
390 | Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Here, what to retrieve depends on what has already been derived, which in turn may depend on what was previously retrieved. To address this, we propose IRCoT, a new approach for multi-step QA that interleaves retrieval with steps (sentences) in a CoT, guiding the retrieval with CoT and in turn using retrieved results to improve CoT. |
Harsh Trivedi; Niranjan Balasubramanian; Tushar Khot; Ashish Sabharwal; | acl | 2023-07-08 |
391 | Improving Pretraining Techniques for Code-Switched NLP Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we explore different masked language modeling (MLM) pretraining techniques for code-switched text that are cognizant of language boundaries prior to masking. |
Richeek Das; Sahasra Ranjan; Shreya Pathak; Preethi Jyothi; | acl | 2023-07-08 |
392 | Content Moderation for Evolving Policies Using Binary Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose to model content moderation as a binary question answering problem where the questions validate the loosely coupled themes constituting a policy. |
SANKHA SUBHRA MULLICK et. al. | acl | 2023-07-08 |
393 | Dynamic Heterogeneous-Graph Reasoning with Language Models and Knowledge Representation Learning for Commonsense Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a dynamic heterogeneous-graph reasoning method with LMs and knowledge representation learning (DHLK), which constructs a heterogeneous knowledge graph (HKG) based on multiple knowledge sources and optimizes the structure and knowledge representation of the HKG using a two-stage pruning strategy and knowledge representation learning (KRL). |
Yujie Wang; Hu Zhang; Jiye Liang; Ru Li; | acl | 2023-07-08 |
394 | History Semantic Graph Enhanced Conversational KBQA with Temporal Information Modeling Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a History Semantic Graph Enhanced KBQA model (HSGE) that is able to effectively model long-range semantic dependencies in conversation history while maintaining low computational cost. |
HAO SUN et. al. | acl | 2023-07-08 |
395 | What Is The Real Intention Behind This Question? Dataset Collection and Intention Classification Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper is the first study to introduce a dataset (Question Intention Dataset) that includes questions with positive/neutral and negative intentions and the underlying intention categories within each group. |
Maryam Sadat Mirzaei; Kourosh Meshgi; Satoshi Sekine; | acl | 2023-07-08 |
396 | Tab-CQA: A Tabular Conversational Question Answering Dataset on Financial Reports Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose Tab-CQA, a tabular CQA dataset created from Chinese financial reports that are extracted from listed companies in a wide range of different sectors in the past 30 years. |
Chuang Liu; Junzhuo Li; Deyi Xiong; | acl | 2023-07-08 |
397 | MeetingQA: Extractive Question-Answering on Meeting Transcripts Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, meeting discussions also have a useful question-answering (QA) component, crucial to understanding the discourse or meeting content, and can be used to build interactive interfaces on top of long transcripts. Hence, in this work, we leverage this inherent QA component of meeting discussions and introduce MeetingQA, an extractive QA dataset comprising of questions asked by meeting participants and corresponding responses. |
ARCHIKI PRASAD et. al. | acl | 2023-07-08 |
398 | Knowledgeable Parameter Efficient Tuning Network for Commonsense Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a simple knowledgeable parameter efficient tuning network to couple PLMs with external knowledge for commonsense question answering. |
Ziwang Zhao; Linmei Hu; Hanyu Zhao; Yingxia Shao; Yequan Wang; | acl | 2023-07-08 |
399 | Long-Tailed Question Answering in An Open World Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we define Open Long-Tailed QA (OLTQA) as learning from long-tailed distributed data and optimizing performance over seen and unseen QA tasks. |
Yi Dai; Hao Lang; Yinhe Zheng; Fei Huang; Yongbin Li; | acl | 2023-07-08 |
400 | Accurate Training of Web-based Question Answering Systems with Feedback from Ranked Users Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we first collect a large scale (16M) QA dataset with real feedback sampled from the QA traffic of a popular Virtual Assistant. Second, we use this data to develop two strategies for filtering unreliable users and thus de-noise feedback: (i) ranking users with an automatic classifier, and (ii) aggregating feedback over similar instances and comparing users between each other. |
Liang Wang; Ivano Lauriola; Alessandro Moschitti; | acl | 2023-07-08 |
401 | Event Extraction As Question Generation and Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we propose QGA-EE, which enables a Question Generation (QG) model to generate questions that incorporate rich contextual information instead of using fixed templates. |
Di Lu; Shihao Ran; Joel Tetreault; Alejandro Jaimes; | acl | 2023-07-08 |
402 | Context-Aware Transformer Pre-Training for Answer Sentence Selection Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose three pre-training objectives designed to mimic the downstream fine-tuning task of contextual AS2. |
Luca Di Liello; Siddhant Garg; Alessandro Moschitti; | acl | 2023-07-08 |
403 | A Survey for Efficient Open Domain Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we will survey recent advancements in the efficiency of ODQA models and conclude core techniques for achieving efficiency. |
QIN ZHANG et. al. | acl | 2023-07-08 |
404 | AlignScore: Evaluating Factual Consistency with A Unified Alignment Function Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we propose AlignScore, a new holistic metric that applies to a variety of factual inconsistency scenarios as above. |
Yuheng Zha; Yichi Yang; Ruichen Li; Zhiting Hu; | acl | 2023-07-08 |
405 | Few-shot Reranking for Multi-hop QA Via Language Model Prompting Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: To alleviate the need for a large number of labeled question-document pairs for retriever training, we propose PromptRank, which relies on language model prompting for multi-hop path reranking. |
Muhammad Khalifa; Lajanugen Logeswaran; Moontae Lee; Honglak Lee; Lu Wang; | acl | 2023-07-08 |
406 | WebCPM: Interactive Web Search for Chinese Long-form Question Answering IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we introduce WebCPM, the first Chinese LFQA dataset. |
YUJIA QIN et. al. | acl | 2023-07-08 |
407 | Towards Benchmarking and Improving The Temporal Reasoning Capability of Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we introduce a comprehensive probing dataset TempReason to evaluate the temporal reasoning capability of large language models. |
Qingyu Tan; Hwee Tou Ng; Lidong Bing; | acl | 2023-07-08 |
408 | FACTIFY-5WQA: 5W Aspect-based Fact Verification Through Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a 5W framework (who, what, when, where, and why) for question-answer-based fact explainability. |
ANKU RANI et. al. | acl | 2023-07-08 |
409 | Won�t Get Fooled Again: Answering Questions with False Premises Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Such frailties of PLMs often allude to the lack of knowledge within them. In this paper, we find that the PLMs already possess the knowledge required to rebut such questions, and the key is how to activate the knowledge. |
SHENGDING HU et. al. | acl | 2023-07-08 |
410 | BUCA: A Binary Classification Approach to Unsupervised Commonsense Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose to transform the downstream multiple choice question answering task into a simpler binary classification task by ranking all candidate answers according to their reasonableness. |
Jie He; Simon U; Victor Gutierrez-Basulto; Jeff Pan; | acl | 2023-07-08 |
411 | Do I Have The Knowledge to Answer? Investigating Answerability of Knowledge Base Questions Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We create GrailQAbility, a new benchmark KBQA dataset with unanswerability, by first identifying various forms of KB incompleteness that make questions unanswerable, and then systematically adapting GrailQA (a popular KBQA dataset with only answerable questions). |
MAYUR PATIDAR et. al. | acl | 2023-07-08 |
412 | CREPE: Open-Domain Question Answering with False Presuppositions Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We introduce CREPE, a QA dataset containing a natural distribution of presupposition failures from online information-seeking forums. |
Xinyan Yu; Sewon Min; Luke Zettlemoyer; Hannaneh Hajishirzi; | acl | 2023-07-08 |
413 | Zero-shot Cross-lingual Transfer With Learned Projections Using Unlabeled Target-Language Data Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We construct language-specific subspaces using standard linear algebra constructs and selectively project source-language representations into the target language subspace during task-specific finetuning using two schemes. |
Ujan Deb; Ridayesh Parab; Preethi Jyothi; | acl | 2023-07-08 |
414 | LI-RAGE: Late Interaction Retrieval Augmented Generation with Explicit Signals for Open-Domain Table Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: These fixed vectors can be insufficient to capture fine-grained features of potentially very big tables with heterogeneous row/column information. We address this limitation by 1) applying late interaction models which enforce a finer-grained interaction between question and table embeddings at retrieval time. In addition, we 2) incorporate a joint training scheme of the retriever and reader with explicit table-level signals, and 3) embed a binary relevance token as a prefix to the answer generated by the reader, so we can determine at inference time whether the table used to answer the question is reliable and filter accordingly. |
Weizhe Lin; Rexhina Blloshmi; Bill Byrne; Adria de Gispert; Gonzalo Iglesias; | acl | 2023-07-08 |
415 | Post-Abstention: Towards Reliably Re-Attempting The Abstained Instances in QA Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To this end, we present an explorative study on �Post-Abstention�, a task that allows re-attempting the abstained instances with the aim of increasing **coverage** of the system without significantly sacrificing its **accuracy**. |
Neeraj Varshney; Chitta Baral; | acl | 2023-07-08 |
416 | Multi-Source Test-Time Adaptation As Dueling Bandits for Extractive Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we study multi-source test-time model adaptation from user feedback, where K distinct models are established for adaptation. |
Hai Ye; Qizhe Xie; Hwee Tou Ng; | acl | 2023-07-08 |
417 | WikiHowQA: A Comprehensive Benchmark for Multi-Document Non-Factoid Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: There is a critical need for high-quality resources for multi-document NFQA (MD-NFQA) to train new models and evaluate answers? grounding and factual consistency in relation to supporting documents. To address this gap, we introduce WikiHowQA, a new multi-document NFQA benchmark built on WikiHow, a website dedicated to answering ?how-to? questions. |
Valeriia Bolotova-Baranova; Vladislav Blinov; Sofya Filippova; Falk Scholer; Mark Sanderson; | acl | 2023-07-08 |
418 | IM-TQA: A Chinese Table Question Answering Dataset with Implicit and Multi-type Table Structures Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Correspondingly, we propose an RGCN-RCI framework outperforming recent baselines. |
MINGYU ZHENG et. al. | acl | 2023-07-08 |
419 | Answering Ambiguous Questions Via Iterative Prompting Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we present AmbigPrompt to address the imperfections of existing approaches to answering ambiguous questions. |
WEIWEI SUN et. al. | arxiv-cs.CL | 2023-07-08 |
420 | WeCheck: Strong Factual Consistency Checker Via Weakly Supervised Learning Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Bias in synthetic text or upstream tasks makes them perform poorly on text actually generated by language models, especially for general evaluation for various tasks. To alleviate this problem, we propose a weakly supervised framework named WeCheck that is directly trained on actual generated samples from language models with weakly annotated labels. |
WENHAO WU et. al. | acl | 2023-07-08 |
421 | Reasoning Over Hierarchical Question Decomposition Tree for Explainable Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose to leverage question decomposing for heterogeneous knowledge integration, by breaking down a complex question into simpler ones, and selecting the appropriate knowledge source for each sub-question. |
JIAJIE ZHANG et. al. | acl | 2023-07-08 |
422 | RobuT: A Systematic Study of Table QA Robustness Against Human-Annotated Adversarial Perturbations Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Our results indicate that both state-of-the-art Table QA models and large language models (e. g. , GPT-3) with few-shot learning falter in these adversarial sets. We propose to address this problem by using large language models to generate adversarial examples to enhance training, which significantly improves the robustness of Table QA models. |
YILUN ZHAO et. al. | acl | 2023-07-08 |
423 | Improving Knowledge Production Efficiency With Question Answering on Conversation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The challenges of conversation-based QA include: 1) answers may be scattered among multiple dialogue turns; 2) understanding complex dialogue contexts is more complicated than documents. To address these challenges, we propose a multi-span extraction model on this task and introduce continual pre-training and multi-task learning schemes to further improve model performance. |
CHANGLIN YANG et. al. | acl | 2023-07-08 |
424 | LexSym: Compositionality As Lexical Symmetry Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we present a domain-general and model-agnostic formulation of compositionality as a constraint on symmetries of data distributions rather than models. |
Ekin Akyurek; Jacob Andreas; | acl | 2023-07-08 |
425 | Using Contradictions Improves Question Answering Systems Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This work examines the use of contradiction in natural language inference (NLI) for question answering (QA). |
Etienne Fortier-Dubois; Domenic Rosati; | acl | 2023-07-08 |
426 | Query Refinement Prompts for Closed-Book Long-Form QA Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We resolve the difficulties to evaluate long-form output by doing both tasks at once ? to do question answering that requires long-form answers. Such questions tend to be multifaceted, i. e. , they may have ambiguities and/or require information from multiple sources. |
Reinald Kim Amplayo; Kellie Webster; Michael Collins; Dipanjan Das; Shashi Narayan; | acl | 2023-07-08 |
427 | MultiTabQA: Generating Tabular Answers for Multi-Table Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Furthermore, multi-table operations often result in a tabular output, which necessitates table generation capabilities of tabular QA models. To fill this gap, we propose a new task of answering questions over multiple tables. |
Vaishali Pal; Andrew Yates; Evangelos Kanoulas; Maarten de Rijke; | acl | 2023-07-08 |
428 | Single Sequence Prediction Over Reasoning Graphs for Multi-hop QA Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: While such models can lead to better interpretability and high quantitative scores, they often have difficulty accurately identifying the passages corresponding to key entities in the context, resulting in incorrect passage hops and a lack of faithfulness in the reasoning path. To address this, we propose a single-sequence prediction method over a local reasoning graph that integrates a graph structure connecting key entities in each context passage to relevant subsequent passages for each question. |
Gowtham Ramesh; Makesh Narsimhan Sreedhar; Junjie Hu; | acl | 2023-07-08 |
429 | S3HQA: A Three-Stage Approach for Multi-hop Text-Table Hybrid Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a three-stage TextTableQA framework S3HQA, which comprises of retriever, selector, and reasoner. |
FANGYU LEI et. al. | acl | 2023-07-08 |
430 | Multi-Row, Multi-Span Distant Supervision For Table+Text Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This leads to a noisy multi-instance training regime. We present MITQA, a transformer-based TextTableQA system that is explicitly designed to cope with distant supervision along both these axes, through a multi-instance loss objective, together with careful curriculum design. |
VISHWAJEET KUMAR et. al. | acl | 2023-07-08 |
431 | SVIT: Scaling Up Visual Instruction Tuning Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Thanks to the emerging of foundation models, the large language and vision models are integrated to acquire the multimodal ability of visual captioning, dialogue, question answering, etc. |
Bo Zhao; Boya Wu; Tiejun Huang; | arxiv-cs.CV | 2023-07-08 |
432 | Task-Aware Specialization for Efficient and Robust Dense Retrieval for Open-Domain Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We thus propose a new architecture, Task-Aware Specialization for dEnse Retrieval (TASER), which enables parameter sharing by interleaving shared and specialized blocks in a single encoder. |
Hao Cheng; Hao Fang; Xiaodong Liu; Jianfeng Gao; | acl | 2023-07-08 |
433 | Do Question Answering Modeling Improvements Hold Across Benchmarks? Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Do question answering (QA) modeling improvements (e. g. , choice of architecture and training procedure) hold consistently across the diverse landscape of QA benchmarks? To study this question, we introduce the notion of concurrence�two benchmarks have high concurrence on a set of modeling approaches if they rank the modeling approaches similarly. |
Nelson F. Liu; Tony Lee; Robin Jia; Percy Liang; | acl | 2023-07-08 |
434 | Reading Between The Lanes: Text VideoQA on The Road Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Systems that exploit such information to assist the driver should not only extract and incorporate visual and textual cues from the video stream but also reason over time. To address this issue, we introduce RoadTextVQA, a new dataset for the task of video question answering (VideoQA) in the context of driver assistance. |
George Tom; Minesh Mathew; Sergi Garcia; Dimosthenis Karatzas; C. V. Jawahar; | arxiv-cs.CV | 2023-07-08 |
435 | Faithful Question Answering with Monte-Carlo Planning Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we propose FAME (FAithful question answering with MontE-carlo planning) to answer questions based on faithful reasoning steps. |
Ruixin Hong; Hongming Zhang; Hong Zhao; Dong Yu; Changshui Zhang; | acl | 2023-07-08 |
436 | Modular Visual Question Answering Via Code Generation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We present a framework that formulates visual question answering as modular code generation. |
SANJAY SUBRAMANIAN et. al. | acl | 2023-07-08 |
437 | Elaboration-Generating Commonsense Question Answering at Scale Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In question answering requiring common sense, language models (e. g. , GPT-3) have been used to generate text expressing background knowledge that helps improve performance. Yet the cost of working with such models is very high; in this work, we finetune smaller language models to generate useful intermediate context, referred to here as elaborations. |
Wenya Wang; Vivek Srikumar; Hannaneh Hajishirzi; Noah A. Smith; | acl | 2023-07-08 |
438 | Concise Answers to Complex Questions: Summarization of Long-form Answers Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Together, we present the first study on summarizing long-form answers, taking a step forward for QA agents that can provide answers at multiple granularities. |
Abhilash Potluri; Fangyuan Xu; Eunsol Choi; | acl | 2023-07-08 |
439 | Product Question Answering in E-Commerce: A Survey Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we aim to systematically review existing research efforts on PQA. |
Yang Deng; Wenxuan Zhang; Qian Yu; Wai Lam; | acl | 2023-07-08 |
440 | Chain-of-Skills: A Configurable Model for Open-Domain Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we propose a modular retriever where individual modules correspond to key skills that can be reused across datasets. |
KAIXIN MA et. al. | acl | 2023-07-08 |
441 | Answering Unanswered Questions Through Semantic Reformulations in Spoken QA Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a Semantic Question Reformulation (SURF) model offering three linguistically-grounded operations (repair, syntactic reshaping, generalization) to rewrite questions to facilitate answering. |
Pedro Faustini; Zhiyu Chen; Besnik Fetahu; Oleg Rokhlenko; Shervin Malmasi; | acl | 2023-07-08 |
442 | Multi-granularity Temporal Question Answering Over Knowledge Graphs Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To overcome the limitation, in this paper, we motivate the notion of multi-granularity temporal question answering over knowledge graphs and present a large scale dataset for multi-granularity TKGQA, namely MultiTQ. |
Ziyang Chen; Jinzhi Liao; Xiang Zhao; | acl | 2023-07-08 |
443 | Peek Across: Improving Multi-Document Modeling Via Cross-Document Question-Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: The integration of multi-document pre-training objectives into language models has resulted in remarkable improvements in multi-document downstream tasks. In this work, we propose extending this idea by pre-training a generic multi-document model from a novel cross-document question answering pre-training objective. |
Avi Caciularu; Matthew Peters; Jacob Goldberger; Ido Dagan; Arman Cohan; | acl | 2023-07-08 |
444 | A Critical Evaluation of Evaluations for Long-form Question Answering IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We present a careful analysis of experts� evaluation, which focuses on new aspects such as the comprehensiveness of the answer. |
Fangyuan Xu; Yixiao Song; Mohit Iyyer; Eunsol Choi; | acl | 2023-07-08 |
445 | Say What You Mean! Large Language Models Speak Too Positively About Negative Commonsense Knowledge Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: This work examines the ability of LLMs on negative commonsense knowledge. |
JIANGJIE CHEN et. al. | acl | 2023-07-08 |
446 | Question-Answering in A Low-resourced Language: Benchmark Dataset and Models for Tigrinya Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This work presents a native QA dataset for an East African language, Tigrinya. |
Fitsum Gaim; Wonsuk Yang; Hancheol Park; Jong Park; | acl | 2023-07-08 |
447 | An Inner Table Retriever for Robust Table Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose Inner Table Retriever (ITR), a general-purpose approach for handling long tables in TableQA that extracts sub-tables to preserve the most relevant information for a question. |
Weizhe Lin; Rexhina Blloshmi; Bill Byrne; Adria de Gispert; Gonzalo Iglesias; | acl | 2023-07-08 |
448 | Learning Answer Generation Using Supervision from Automatic Question Answering Evaluators Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a novel training paradigm for GenQA using supervision from automatic QA evaluation models (GAVA). |
Matteo Gabburo; Siddhant Garg; Rik Koncel-Kedziorski; Alessandro Moschitti; | acl | 2023-07-08 |
449 | To Adapt or to Annotate: Challenges and Interventions for Domain Adaptation in Open-Domain Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This work proposes a more realistic end-to-end domain shift evaluation setting covering five diverse domains. |
Dheeru Dua; Emma Strubell; Sameer Singh; Pat Verga; | acl | 2023-07-08 |
450 | Few-shot In-context Learning on Knowledge Base Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To handle questions over diverse KBQA datasets with a unified training-free framework, we propose KB-BINDER, which for the first time enables few-shot in-context learning over KBQA tasks. |
TIANLE LI et. al. | acl | 2023-07-08 |
451 | (QA)2: Question Answering with Questionable Assumptions Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we propose (QA)2 (Question Answering with Questionable Assumptions), an open-domain evaluation dataset consisting of naturally occurring search engine queries that may or may not contain questionable assumptions. |
Najoung Kim; Phu Mon Htut; Samuel R. Bowman; Jackson Petty; | acl | 2023-07-08 |
452 | Evaluating Open-Domain Question Answering in The Era of Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we conduct a thorough analysis of various open-domain QA models, including LLMs, by manually evaluating their answers on a subset of NQ-open, a popular benchmark. |
Ehsan Kamalloo; Nouha Dziri; Charles Clarke; Davood Rafiei; | acl | 2023-07-08 |
453 | UIT-Saviors at MEDVQA-GI 2023: Improving Multimodal Learning with Image Enhancement for Gastrointestinal Visual Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Our team approached Task 1 of the challenge by proposing a multimodal learning method with image enhancement to improve the VQA performance on gastrointestinal images. |
Triet M. Thai; Anh T. Vo; Hao K. Tieu; Linh N. P. Bui; Thien T. B. Nguyen; | arxiv-cs.CV | 2023-07-06 |
454 | VisKoP: Visual Knowledge Oriented Programming for Interactive Knowledge Base Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present Visual Knowledge oriented Programming platform (VisKoP), a knowledge base question answering (KBQA) system that integrates human into the loop to edit and debug the knowledge base (KB) queries. |
ZIJUN YAO et. al. | arxiv-cs.CL | 2023-07-06 |
455 | Text Alignment Is An Efficient Unified Model for Massive NLP Tasks Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose text alignment as an efficient unified model for a wide range of crucial tasks involving text entailment, similarity, question answering (and answerability), factual consistency, and so forth. |
Yuheng Zha; Yichi Yang; Ruichen Li; Zhiting Hu; | arxiv-cs.CL | 2023-07-05 |
456 | Won’t Get Fooled Again: Answering Questions with False Premises Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Such frailties of PLMs often allude to the lack of knowledge within them. In this paper, we find that the PLMs already possess the knowledge required to rebut such questions, and the key is how to activate the knowledge. |
SHENGDING HU et. al. | arxiv-cs.CL | 2023-07-05 |
457 | Localized Questions in Medical Visual Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Consequently, VQA models are limited in their interpretability power and the possibility to probe the model about specific image regions. This paper proposes a novel approach for medical VQA that addresses this limitation by developing a model that can answer questions about image regions while considering the context necessary to answer the questions. |
Sergio Tascon-Morales; Pablo Márquez-Neila; Raphael Sznitman; | arxiv-cs.CV | 2023-07-03 |
458 | Modeling Tag Prediction Based on Question Tagging Behavior Analysis of CommunityQA Platform Users Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To develop better tag prediction across diverse communities and domains, we performed a thorough analysis of users’ tagging behavior in 17 StackExchange communities. |
Kuntal Kumar Pal; Michael Gamon; Nirupama Chandrasekaran; Silviu Cucerzan; | arxiv-cs.CL | 2023-07-03 |
459 | Single Sequence Prediction Over Reasoning Graphs for Multi-hop QA Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: While such models can lead to better interpretability and high quantitative scores, they often have difficulty accurately identifying the passages corresponding to key entities in the context, resulting in incorrect passage hops and a lack of faithfulness in the reasoning path. To address this, we propose a single-sequence prediction method over a local reasoning graph (\model)\footnote{Code/Models will be released at \url{https://github.com/gowtham1997/SeqGraph}} that integrates a graph structure connecting key entities in each context passage to relevant subsequent passages for each question. |
Gowtham Ramesh; Makesh Sreedhar; Junjie Hu; | arxiv-cs.CL | 2023-07-01 |
460 | Multimodal Prompt Retrieval for Generative Visual Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Despite the recent advances in VQA, existing methods mainly adopt a discriminative formulation that predicts answers within a pre-defined label set, leading to easy overfitting on low-resource domains with limited labeled data (e.g., medicine) and poor generalization under domain shift to another dataset. To tackle this limitation, we propose a novel generative model enhanced by multimodal prompt retrieval (MPR) that integrates retrieved prompts and multimodal features to generate answers in free text. |
Timothy Ossowski; Junjie Hu; | arxiv-cs.CV | 2023-06-30 |
461 | Unified Language Representation for Question Answering Over Text, Tables, and Images Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we call for an alternative paradigm, which transforms the images and tables into unified language representations, so that we can simplify the task into a simpler textual QA problem that can be solved using three steps: retrieval, ranking, and generation, all within a language space. |
Bowen Yu; Cheng Fu; Haiyang Yu; Fei Huang; Yongbin Li; | arxiv-cs.CL | 2023-06-29 |
462 | SE-PQA: Personalized Community Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We describe the characteristics of SE-PQA and detail the features associated with questions and answers. |
Pranav Kasela; Gabriella Pasi; Raffaele Perego; | arxiv-cs.IR | 2023-06-28 |
463 | Pre-Training Multi-Modal Dense Retrievers for Outside-Knowledge Visual Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We propose an automatic data generation pipeline for pre-training passage retrieval models for OK-VQA tasks. |
Alireza Salemi; Mahta Rafiee; Hamed Zamani; | arxiv-cs.IR | 2023-06-28 |
464 | QASA: Advanced Question Answering on Scientific Articles Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Based on our intensive think-aloud study that revealed the three types of questions: surface, testing, and deep questions, we first propose the QASA benchmark that consists of 1798 novel question answering pairs that require full-stack reasoning on scientific articles in AI and ML fields. Then we propose the QASA approach that tackles the full-stack reasoning with large language models via associative selection, evidential rationale-generation, and systematic composition. |
YOONJOO LEE et. al. | icml | 2023-06-27 |
465 | Motion Question Answering Via Modular Motion Programs Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In order to build artificial intelligence systems that can perceive and reason with human behavior in the real world, we must first design models that conduct complex spatio-temporal reasoning over motion sequences. Moving towards this goal, we propose the HumanMotionQA task to evaluate complex, multi-step reasoning abilities of models on long-form human motion sequences |
Mark Endo; Joy Hsu; Jiaman Li; Jiajun Wu; | icml | 2023-06-27 |
466 | Variational Open-Domain Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We introduce the Variational Open-Domain (VOD) framework for end-to-end training and evaluation of retrieval-augmented models, focusing on open-domain question answering and language modelling. |
Valentin Liévin; Andreas Geert Motzfeldt; Ida Riis Jensen; Ole Winther; | icml | 2023-06-27 |
467 | ILLUME: Rationalizing Vision-Language Models Through Human Interactions Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: However, outputs of these models rarely align with user’s rationales for specific answers. In order to improve this alignment and reinforce commonsense reasons, we propose a tuning paradigm based on human interactions with machine-generated data. |
Manuel Brack; Patrick Schramowski; Björn Deiseroth; Kristian Kersting; | icml | 2023-06-27 |
468 | Knowledge-Constrained Answer Generation for Open-Ended Video Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a Knowledge-constrained Generative VideoQA Algorithm (KcGA) with an encoder-decoder pipeline, which enables out-of-domain answer generation through an adaptive external knowledge module and a multi-stream information control mechanism. |
YAO JIN et. al. | aaai | 2023-06-26 |
469 | MPMQA: Multimodal Question Answering on Product Manuals Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, to emphasize the importance of multimodal contents, we propose a Multimodal Product Manual Question Answering (MPMQA) task. |
Liang Zhang; Anwen Hu; Jing Zhang; Shuo Hu; Qin Jin; | aaai | 2023-06-26 |
470 | Fauno: The Italian Large Language Model That Will Leave You Senza Parole! Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: This paper presents Fauno, the first and largest open-source Italian conversational Large Language Model (LLM). |
Andrea Bacciu; Giovanni Trappolini; Andrea Santilli; Emanuele Rodolà; Fabrizio Silvestri; | arxiv-cs.CL | 2023-06-26 |
471 | LIQUID: A Framework for List Question Answering Dataset Generation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Although several recent studies have aimed to generate synthetic questions with single-span answers, no study has been conducted on the creation of list questions with multiple, non-contiguous spans as answers. To address this gap, we propose LIQUID, an automated framework for generating list QA datasets from unlabeled corpora. |
Seongyun Lee; Hyunjae Kim; Jaewoo Kang; | aaai | 2023-06-26 |
472 | A Question-Answering Approach to Key Value Pair Extraction from Form-Like Document Images Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we present a new question-answering (QA) based key-value pair extraction approach, called KVPFormer, to robustly extracting key-value relationships between entities from form-like document images. |
KAI HU et. al. | aaai | 2023-06-26 |
473 | FiTs: Fine-Grained Two-Stage Training for Knowledge-Aware Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Despite the promising result of recent KAQA systems which tend to integrate linguistic knowledge from pre-trained language models (PLM) and factual knowledge from knowledge graphs (KG) to answer complex questions, a bottleneck exists in effectively fusing the representations from PLMs and KGs because of (i) the semantic and distributional gaps between them, and (ii) the difficulties in joint reasoning over the provided knowledge from both modalities. To address the above two problems, we propose a Fine-grained Two-stage training framework (FiTs) to boost the KAQA system performance: The first stage aims at aligning representations from the PLM and the KG, thus bridging the modality gaps between them, named knowledge adaptive post-training. |
Qichen Ye; Bowen Cao; Nuo Chen; Weiyuan Xu; Yuexian Zou; | aaai | 2023-06-26 |
474 | Improving The Cross-Lingual Generalisation in Visual Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: While several benefits were realized for multilingual vision-language pretrained models, recent benchmarks across various tasks and languages showed poor cross-lingual generalisation when multilingually pre-trained vision-language models are applied to non-English data, with a large gap between (supervised) English performance and (zero-shot) cross-lingual transfer. In this work, we explore the poor performance of these models on a zero-shot cross-lingual visual question answering (VQA) task, where models are fine-tuned on English visual-question data and evaluated on 7 typologically diverse languages. |
Farhad Nooralahzadeh; Rico Sennrich; | aaai | 2023-06-26 |
475 | Which Shortcut Solution Do Question Answering Models Prefer to Learn? Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Thus, we first examine the learnability of the representative shortcuts on extractive and multiple-choice QA datasets. Behavioral tests using biased training sets reveal that shortcuts that exploit answer positions and word-label correlations are preferentially learned for extractive and multiple-choice QA, respectively. We find that the more learnable a shortcut is, the flatter and deeper the loss landscape is around the shortcut solution in the parameter space. |
Kazutoshi Shinoda; Saku Sugawara; Akiko Aizawa; | aaai | 2023-06-26 |
476 | STOA-VLP: Spatial-Temporal Modeling of Object and Action for Video-Language Pre-training Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we propose STOA-VLP, a pre-training framework that jointly models object and action information across spatial and temporal dimensions. |
WEIHONG ZHONG et. al. | aaai | 2023-06-26 |
477 | HybridPrompt: Bridging Language Models and Human Priors in Prompt Tuning for Visual Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: They generally do not integrate human priors to compensate for universal knowledge from language models, so as to fit the challenging VQA problem and generate reliable answers. To address these issues, we propose HybridPrompt, a cloze- and verify-style hybrid prompt framework with bridging language models and human priors in prompt tuning for VQA. |
Zhiyuan Ma; Zhihuan Yu; Jianjun Li; Guohui Li; | aaai | 2023-06-26 |
478 | Symbolic Replay: Scene Graph As Prompt for Continual Learning on VQA Task IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Thus, we propose a real-data-free replay-based method tailored for CL on VQA, named Scene Graph as Prompt for Symbolic Replay. |
STAN WEIXIAN LEI et. al. | aaai | 2023-06-26 |
479 | Question Decomposition Tree for Answering Complex Questions Over Knowledge Bases Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we propose Question Decomposition Tree (QDT) to represent the structure of complex questions. |
Xiang Huang; Sitao Cheng; Yiheng Shu; Yuheng Bao; Yuzhong Qu; | aaai | 2023-06-26 |
480 | Relation-Aware Language-Graph Transformer for Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: However, most existing GNN-based modules for QA do not take advantage of rich relational information of KGs and depend on limited information interaction between the LM and the KG. To address these issues, we propose Question Answering Transformer (QAT), which is designed to jointly reason over language and graphs with respect to entity relations in a unified manner. |
JINYOUNG PARK et. al. | aaai | 2023-06-26 |
481 | SPRING: Situated Conversation Agent Pretrained with Multimodal Questions from Incremental Layout Graph Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Existing multimodal conversation agents have shown impressive abilities to locate absolute positions or retrieve attributes in simple scenarios, but they fail to perform well when complex relative positions and information alignments are involved, which poses a bottleneck in response quality. In this paper, we propose a Situated Conversation Agent Pretrained with Multimodal Questions from Incremental Layout Graph (SPRING) with abilities of reasoning multi-hops spatial relations and connecting them with visual attributes in crowded situated scenarios. |
YUXING LONG et. al. | aaai | 2023-06-26 |
482 | FunQA: Towards Surprising Video Comprehension Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We introduce FunQA, a challenging video question answering (QA) dataset specifically designed to evaluate and enhance the depth of video reasoning based on counter-intuitive and fun videos. |
BINZHU XIE et. al. | arxiv-cs.CV | 2023-06-26 |
483 | Efficient End-to-End Video Question Answering with Pyramidal Multimodal Transformer Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: This paper presents a new method for end-to-end Video Question Answering (VideoQA), aside from the current popularity of using large-scale pre-training with huge feature extractors. |
Min Peng; Chongyang Wang; Yu Shi; Xiang-Dong Zhou; | aaai | 2023-06-26 |
484 | Inferential Knowledge-Enhanced Integrated Reasoning for Video Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To this end, we propose an Inferential Knowledge-Enhanced Integrated Reasoning method. |
Jianguo Mao; Wenbin Jiang; Hong Liu; Xiangdong Wang; Yajuan Lyu; | aaai | 2023-06-26 |
485 | SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this study, we propose a new multi-image document VQA dataset, SlideVQA, containing 2.6k+ slide decks composed of 52k+ slide images and 14.5k questions about a slide deck. |
RYOTA TANAKA et. al. | aaai | 2023-06-26 |
486 | Locate Then Generate: Bridging Vision and Language with Bounding Box for Scene-Text VQA Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a novel multi-modal framework for Scene Text Visual Question Answering (STVQA), which requires models to read scene text in images for question answering. |
YONGXIN ZHU et. al. | aaai | 2023-06-26 |
487 | RINK: Reader-Inherited Evidence Reranker for Table-and-Text Open Domain Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we present a Retriever-Reranker-Reader framework by newly proposing a Reader-INherited evidence reranKer (RINK) where a reranker module is designed by finetuning the reader’s neural architecture based on a simple prompting method. |
EUNHWAN PARK et. al. | aaai | 2023-06-26 |
488 | RPA: Reasoning Path Augmentation in Iterative Retrieving for Multi-Hop QA Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Within the RP, two fundamental challenges emerge for better performance: (i) what the order of the justifications in the RP should be, and (ii) what if the wrong justification has been in the path. In this paper, we propose Reasoning Path Augmentation (RPA), which uses reasoning path reordering and augmentation to handle the above two challenges, respectively. |
Ziyi Cao; Bingquan Liu; Shaobo Li; | aaai | 2023-06-26 |
489 | COCA: COllaborative CAusal Regularization for Audio-Visual Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Through detailed causal-graph analyses and careful inspections of their learning processes, we reveal that AVQA models are not only prone to over-exploit prevalent language bias, but also suffer from additional joint-modal biases caused by the shortcut relations between textual-auditory/visual co-occurrences and dominated answers. In this paper, we propose a COllabrative CAusal (COCA) Regularization to remedy this more challenging issue of data biases. |
MINGRUI LAO et. al. | aaai | 2023-06-26 |
490 | Visual Question Answering in Remote Sensing with Cross-Attention and Multimodal Information Bottleneck Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this research, we deal with the problem of visual question answering (VQA) in remote sensing. |
Jayesh Songara; Shivam Pande; Shabnam Choudhury; Biplab Banerjee; Rajbabu Velmurugan; | arxiv-cs.CV | 2023-06-25 |
491 | Retrieving Supporting Evidence for LLMs Generated Answers Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we report a simple experiment to automatically verify generated answers against a corpus. |
Siqing Huo; Negar Arabzadeh; Charles L. A. Clarke; | arxiv-cs.IR | 2023-06-23 |
492 | CompMix: A Benchmark for Heterogeneous Question Answering Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Fact-centric question answering (QA) often requires access to multiple, heterogeneous, information sources. By jointly considering several sources like a knowledge base (KB), a … |
Philipp Christmann; Rishiraj Saha Roy; Gerhard Weikum; | arxiv-cs.IR | 2023-06-21 |
493 | EQUALS: A Real-world Dataset for Legal Question Answering Via Reading Chinese Laws Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Legal Question Answering (LQA) is a promising artificial intelligence application with high practical value. A professional and effective legal question answering (QA) agent can … |
ANDONG CHEN et. al. | Proceedings of the Nineteenth International Conference on … | 2023-06-19 |
494 | Investigating Prompting Techniques for Zero- and Few-Shot Visual Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: This paper explores the use of various prompting strategies, focusing on the BLIP2 model, to enhance zero-shot VQA performance. |
Rabiul Awal; Le Zhang; Aishwarya Agrawal; | arxiv-cs.CV | 2023-06-16 |
495 | Learning to Summarize and Answer Questions About A Virtual Robot’s Past Actions Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To enable training of question answering, we develop a method to automatically generate English-language questions and answers about objects, actions, and the temporal order in which actions occurred during episodes of robot action in the virtual environment. |
Chad DeChant; Iretiayo Akinola; Daniel Bauer; | arxiv-cs.RO | 2023-06-16 |
496 | LVLM-eHub: A Comprehensive Evaluation Benchmark for Large Vision-Language Models IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: This paper presents a comprehensive evaluation of publicly available large multimodal models by building a LVLM evaluation Hub (LVLM-eHub). |
PENG XU et. al. | arxiv-cs.CV | 2023-06-15 |
497 | Encyclopedic VQA: Visual Questions About Detailed Properties of Fine-grained Categories Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We propose Encyclopedic-VQA, a large scale visual question answering (VQA) dataset featuring visual questions about detailed properties of fine-grained categories and instances. |
THOMAS MENSINK et. al. | arxiv-cs.CV | 2023-06-15 |
498 | Retrieving-to-Answer: Zero-Shot Video Question Answering with Frozen Large Language Models Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Video Question Answering (VideoQA) has been significantly advanced from the scaling of recent Large Language Models (LLMs). The key idea is to convert the visual information into … |
JUNTING PAN et. al. | ArXiv | 2023-06-15 |
499 | Improving Selective Visual Question Answering By Learning from Your Peers Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we explore Selective VQA in both in-distribution (ID) and OOD scenarios, where models are presented with mixtures of ID and OOD data. |
CORENTIN DANCETTE et. al. | arxiv-cs.CV | 2023-06-14 |
500 | Scalable Neural-Probabilistic Answer Set Programming Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In our work, we propose an easy integration of tractable probabilistic inference within a DPPL. |
Arseny Skryagin; Daniel Ochs; Devendra Singh Dhami; Kristian Kersting; | arxiv-cs.AI | 2023-06-14 |
501 | AVIS: Autonomous Visual Information Seeking with Large Language Model Agent Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose an autonomous information seeking visual question answering framework, AVIS. |
ZINIU HU et. al. | arxiv-cs.CV | 2023-06-13 |
502 | Improving Opinion-based Question Answering Systems Through Label Error Detection and Overwrite Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose LEDO: a model-agnostic and computationally efficient framework for Label Error Detection and Overwrite. |
XIAO YANG et. al. | arxiv-cs.CL | 2023-06-12 |
503 | Towards The Exploitation of LLM-based Chatbot for Providing Legal Support to Palestinian Cooperatives Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we present our work on a cooperative-legal question-answering LLM-based chatbot, where we developed a set of legal questions about Palestinian cooperatives, associated with their regulations and compared the auto-generated answers by the chatbot to their correspondences that are designed by a legal expert. |
Rabee Qasem; Banan Tantour; Mohammed Maree; | arxiv-cs.CL | 2023-06-09 |
504 | Knowledge Detection By Relevant Question and Image Attributes in Visual Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Some testing questions require external knowledge to derive a solution. |
Param Ahir; Dr. Hiteishi Diwanji; | arxiv-cs.CV | 2023-06-08 |
505 | Privacy Aware Question-Answering System for Online Mental Health Risk Assessment Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a Question-Answering (QA) approach to assess mental health risk using the Unified-QA model on two large mental health datasets. |
Prateek Chhikara; Ujjwal Pasupulety; John Marshall; Dhiraj Chaurasia; Shweta Kumari; | arxiv-cs.CL | 2023-06-08 |
506 | Knowledge-Augmented Language Model Prompting for Zero-Shot Knowledge Graph Question Answering IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To this end, we propose to augment the knowledge directly in the input of LLMs. |
Jinheon Baek; Alham Fikri Aji; Amir Saffari; | arxiv-cs.CL | 2023-06-07 |
507 | When to Read Documents or QA History: On Unified and Selective Open-domain QA Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper studies the problem of open-domain question answering, with the aim of answering a diverse range of questions leveraging knowledge resources. |
Kyungjae Lee; Sang-eun Han; Seung-won Hwang; Moontae Lee; | arxiv-cs.CL | 2023-06-07 |
508 | Enhancing In-Context Learning with Answer Feedback for Multi-Span Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: A popular implementation is to concatenate a few questions and their correct answers through simple templates, informing LLM of the desired output. In this paper, we propose a novel way of employing labeled data such that it also informs LLM of some undesired output, by extending demonstration examples with feedback about answers predicted by an off-the-shelf model, e.g., correct, incorrect, or incomplete. |
Zixian Huang; Jiaying Zhou; Gengyang Xiao; Gong Cheng; | arxiv-cs.CL | 2023-06-07 |
509 | Improving Vietnamese Legal Question–Answering System Based on Automatic Data Enrichment Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: It is even more difficult to perform legal QA for low-resource languages like Vietnamese where labeled data are rare and pre-trained language models are still limited. In this paper, we try to overcome these limitations by implementing a Vietnamese article-level retrieval-based legal QA system and introduce a novel method to improve the performance of language models by improving data quality through weak labeling. |
Thi-Hai-Yen Vuong; Ha-Thanh Nguyen; Quang-Huy Nguyen; Le-Minh Nguyen; Xuan-Hieu Phan; | arxiv-cs.CL | 2023-06-07 |
510 | Phrase Retrieval for Open-Domain Conversational Question Answering with Conversational Dependency Modeling Via Contrastive Learning Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we propose a method to directly predict answers with a phrase retrieval scheme for a sequence of words, reducing the conventional two distinct subtasks into a single one. |
Soyeong Jeong; Jinheon Baek; Sung Ju Hwang; Jong C. Park; | arxiv-cs.CL | 2023-06-07 |
511 | Diversifying Joint Vision-Language Tokenization Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we find that the representations must not only jointly capture features from both modalities but should also be diverse for better generalization performance. |
Vardaan Pahuja; AJ Piergiovanni; Anelia Angelova; | arxiv-cs.CV | 2023-06-06 |
512 | Gotta: Generative Few-shot Question Answering By Prompt-based Cloze Data Augmentation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we develop Gotta, a Generative prOmpT-based daTa Augmentation framework to mitigate the challenge above. |
Xiusi Chen; Yu Zhang; Jinliang Deng; Jyun-Yu Jiang; Wei Wang; | arxiv-cs.CL | 2023-06-06 |
513 | Triggering Multi-Hop Reasoning for Question Answering in Language Models Using Soft Prompts and Random Walks Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Despite readily memorizing world knowledge about entities, pre-trained language models (LMs) struggle to compose together two or more facts to perform multi-hop reasoning in question-answering tasks. In this work, we propose techniques that improve upon this limitation by relying on random walks over structured knowledge graphs. |
Kanishka Misra; Cicero Nogueira dos Santos; Siamak Shakeri; | arxiv-cs.CL | 2023-06-06 |
514 | Benchmarking Large Language Models on CMExam — A Comprehensive Chinese Medical Exam Dataset Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: However, evaluating LLMs in the medical field is challenging due to the lack of standardized and comprehensive datasets. To address this gap, we introduce CMExam, sourced from the Chinese National Medical Licensing Examination. |
JUNLING LIU et. al. | arxiv-cs.CL | 2023-06-05 |
515 | Multi-CLIP: Contrastive Vision-Language Pre-training for Question Answering Tasks in 3D Scenes Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a novel 3D pre-training Vision-Language method, namely Multi-CLIP, that enables a model to learn language-grounded and transferable 3D scene point cloud representations. |
ALEXANDROS DELITZAS et. al. | arxiv-cs.CV | 2023-06-04 |
516 | Evaluation of AI Chatbots for Patient-Specific EHR Questions Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper investigates the use of artificial intelligence chatbots for patient-specific question answering (QA) from clinical notes using several large language model (LLM) based systems: ChatGPT (versions 3.5 and 4), Google Bard, and Claude. |
Alaleh Hamidi; Kirk Roberts; | arxiv-cs.CL | 2023-06-04 |
517 | Question-Context Alignment and Answer-Context Dependencies for Effective Answer Sentence Selection Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose to improve the candidate scoring by explicitly incorporating the dependencies between question-context and answer-context into the final representation of a candidate. |
MINH VAN NGUYEN et. al. | arxiv-cs.CL | 2023-06-03 |
518 | Make Pre-trained Model Reversible: From Parameter to Memory Efficient Fine-Tuning Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we first investigate what is a key factor for the success of existing PEFT methods, and realize that it’s essential to preserve the PLM’s starting point when initializing a PEFT method. With this finding, we propose memory-efficient fine-tuning (MEFT) that inserts adapters into a PLM, preserving the PLM’s starting point and making it reversible without additional pre-training. |
Baohao Liao; Shaomu Tan; Christof Monz; | arxiv-cs.CL | 2023-06-01 |
519 | Overcoming Language Bias in Remote Sensing Visual Question Answering Via Adversarial Training Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, VQA models commonly face the challenge of language bias, resulting from the learned superficial correlation between questions and answers. To address this issue, in this study, we present a novel framework to reduce the language bias of the VQA for remote sensing data (RSVQA). |
Zhenghang Yuan; Lichao Mou; Xiao Xiang Zhu; | arxiv-cs.CV | 2023-06-01 |
520 | Reimagining Retrieval Augmented Language Models for Answering Queries Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a reality check on large language models and inspect the promise of retrieval augmented language models in comparison. |
WANG-CHIEW TAN et. al. | arxiv-cs.CL | 2023-06-01 |
521 | LiT-4-RSVQA: Lightweight Transformer-based Visual Question Answering in Remote Sensing Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Visual question answering (VQA) methods in remote sensing (RS) aim to answer natural language questions with respect to an RS image. |
Leonard Hackel; Kai Norman Clasen; Mahdyar Ravanbakhsh; Begüm Demir; | arxiv-cs.CV | 2023-06-01 |
522 | Layout and Task Aware Instruction Prompt for Zero-shot Document Image Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Instead, in this paper, we find that instruction-tuning language models like Claude and ChatGPT can understand layout by spaces and line breaks. |
Wenjin Wang; Yunhao Li; Yixin Ou; Yin Zhang; | arxiv-cs.CL | 2023-06-01 |
523 | TimelineQA: A Benchmark for Question Answering Over Timelines Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We describe a set of experiments on TimelineQA with several state-of-the-art QA models. |
WANG-CHIEW TAN et. al. | arxiv-cs.CL | 2023-06-01 |
524 | Using Visual Cropping to Enhance Fine-Detail Question Answering of BLIP-Family Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Given the recent success of the BLIP-family models, we study a zero-shot and a fine-tuned BLIP model. |
Jiarui Zhang; Mahyar Khayatkhoei; Prateek Chhikara; Filip Ilievski; | arxiv-cs.CV | 2023-05-31 |
525 | Attention-Based Methods For Audio Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose neural network architectures based on self-attention and cross-attention for the AQA task. |
Parthasaarathy Sudarsanam; Tuomas Virtanen; | arxiv-cs.CL | 2023-05-31 |
526 | UKP-SQuARE: An Interactive Tool for Teaching Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we introduce UKP-SQuARE as a platform for QA education. |
Haishuo Fang; Haritz Puerto; Iryna Gurevych; | arxiv-cs.CL | 2023-05-31 |
527 | Building Extractive Question Answering System to Support Human-AI Health Coaching Model for Sleep Domain Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents a human-Artificial Intelligence (AI) health coaching model incorporating a domain-specific extractive QA system. |
Iva Bojic; Qi Chwen Ong; Shafiq Joty; Josip Car; | arxiv-cs.CL | 2023-05-31 |
528 | Graph Reasoning for Question Answering with Triplet Retrieval Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a simple yet effective method to first retrieve the most relevant triplets from KGs and then rerank them, which are then concatenated with questions to be fed into language models. |
SHIYANG LI et. al. | arxiv-cs.CL | 2023-05-30 |
529 | Generate Then Select: Open-ended Visual Question Answering Guided By World Knowledge Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To address the aforementioned challenges, we propose RASO: a new VQA pipeline that deploys a generate-then-select strategy guided by world knowledge for the first time. |
XINGYU FU et. al. | arxiv-cs.CL | 2023-05-30 |
530 | PaLI-X: On Scaling Up A Multilingual Vision and Language Model IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We present the training recipe and results of scaling up PaLI-X, a multilingual vision and language model, both in terms of size of the components and the breadth of its training task mixture. |
XI CHEN et. al. | arxiv-cs.CV | 2023-05-29 |
531 | Multi-Scale Attention for Audio Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: To this end, we present a Multi-scale Window Attention Fusion Model (MWAFM) consisting of an asynchronous hybrid attention module and a multi-scale window attention module. |
Guangyao Li; Yixin Xu; Di Hu; | arxiv-cs.SD | 2023-05-29 |
532 | Contextual Object Detection with Multimodal Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Recent Multimodal Large Language Models (MLLMs) are remarkable in vision-language tasks, such as image captioning and question answering, but lack the essential perception ability, i.e., object detection. In this work, we address this limitation by introducing a novel research problem of contextual object detection — understanding visible objects within different human-AI interactive contexts. |
Yuhang Zang; Wei Li; Jun Han; Kaiyang Zhou; Chen Change Loy; | arxiv-cs.CV | 2023-05-29 |
533 | KEYword Based Sampling (KEYS) for Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In the research community, very little focus is on how humans generate answers to a question and how this behavior can be incorporated in a language model. In this paper, we want to explore these two areas combined, i.e., how sampling can be to used generate answers which are close to human-like behavior and factually correct. |
Jyothir S V; Zuhaib Akhtar; | arxiv-cs.CL | 2023-05-29 |
534 | Breaking Language Barriers with A LEAP: Learning Strategies for Polyglot LLMs Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Through systematic investigation and evaluation of diverse languages using popular question-answering (QA) datasets, we present novel techniques that unlock the true potential of LLMs in a polyglot landscape. |
AKSHAY NAMBI et. al. | arxiv-cs.CL | 2023-05-28 |
535 | HaVQA: A Dataset for Visual Question Answering and Multimodal Research in Hausa Language Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents HaVQA, the first multimodal dataset for visual question-answering (VQA) tasks in the Hausa language. |
SHANTIPRIYA PARIDA et. al. | arxiv-cs.CL | 2023-05-28 |
536 | Conformal Prediction with Large Language Models for Multi-Choice Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we explore how conformal prediction can be used to provide uncertainty quantification in language models for the specific task of multiple-choice question-answering. |
BHAWESH KUMAR et. al. | arxiv-cs.CL | 2023-05-28 |
537 | Expand, Rerank, and Retrieve: Query Reranking for Open-Domain Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We propose EAR, a query Expansion And Reranking approach for improving passage retrieval, with the application to open-domain question answering. |
Yung-Sung Chuang; Wei Fang; Shang-Wen Li; Wen-tau Yih; James Glass; | arxiv-cs.CL | 2023-05-26 |
538 | An Empirical Comparison of LM-based Question and Answer Generation Methods Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we establish baselines with three different QAG methodologies that leverage sequence-to-sequence language model (LM) fine-tuning. |
Asahi Ushio; Fernando Alva-Manchego; Jose Camacho-Collados; | arxiv-cs.CL | 2023-05-26 |
539 | Exploiting Abstract Meaning Representation for Open-Domain Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We introduce a method known as Graph-as-Token (GST) to incorporate AMRs into PLMs. |
CUNXIANG WANG et. al. | arxiv-cs.CL | 2023-05-26 |
540 | RFiD: Towards Rational Fusion-in-Decoder for Open-Domain Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Although representative models like Fusion-in-Decoder (FiD) have been proposed to address this challenge, these systems can inadvertently rely on spurious features instead of genuine causal relationships between the question and the passages to generate answers. To counter this problem, we introduce the Rational Fusion-in-Decoder (RFiD) model. |
Cunxiang Wang; Haofei Yu; Yue Zhang; | arxiv-cs.CL | 2023-05-26 |
541 | Zero-shot Visual Question Answering with Language Model Feedback Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we propose a novel language model guided captioning approach, LAMOC, for knowledge-based visual question answering (VQA). |
Yifan Du; Junyi Li; Tianyi Tang; Wayne Xin Zhao; Ji-Rong Wen; | arxiv-cs.CV | 2023-05-26 |
542 | BUCA: A Binary Classification Approach to Unsupervised Commonsense Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose to transform the downstream multiple choice question answering task into a simpler binary classification task by ranking all candidate answers according to their reasonableness. |
Jie He; Simon Chi Lok U; Víctor Gutiérrez-Basulto; Jeff Z. Pan; | arxiv-cs.CL | 2023-05-25 |
543 | UFO: Unified Fact Obtaining for Commonsense Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We propose a Unified Facts Obtaining (UFO) approach. |
Zhifeng Li; Yifan Fan; Bowei Zou; Yu Hong; | arxiv-cs.CL | 2023-05-25 |
544 | The Dangers of Trusting Stochastic Parrots: Faithfulness and Trust in Open-domain Conversational Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we show that task-based systems which exhibit certain advanced linguistic dialog behaviors, such as lexical alignment (repeating what the user said), are in fact preferred and trusted more, whereas other phenomena, such as pronouns and ellipsis are dis-preferred. |
SABRINA CHIESURIN et. al. | arxiv-cs.CL | 2023-05-25 |
545 | Comparing Humans and Models on A Similar Scale: Towards Cognitive Gender Bias Evaluation in Coreference Resolution Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work we address the question: can we quantify the extent to which model biases reflect human behaviour? |
Gili Lior; Gabriel Stanovsky; | arxiv-cs.CL | 2023-05-24 |
546 | Peek Across: Improving Multi-Document Modeling Via Cross-Document Question-Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: The integration of multi-document pre-training objectives into language models has resulted in remarkable improvements in multi-document downstream tasks. In this work, we propose extending this idea by pre-training a generic multi-document model from a novel cross-document question answering pre-training objective. |
Avi Caciularu; Matthew E. Peters; Jacob Goldberger; Ido Dagan; Arman Cohan; | arxiv-cs.CL | 2023-05-24 |
547 | Spoken Question Answering and Speech Continuation Using Spectrogram-Powered LLM Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a novel approach to adapting pre-trained large language models (LLMs) to perform question answering (QA) and speech continuation. |
ELIYA NACHMANI et. al. | arxiv-cs.CL | 2023-05-24 |
548 | UniChart: A Universal Vision-language Pretrained Model for Chart Comprehension and Reasoning Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We propose several chart-specific pretraining tasks that include: (i) low-level tasks to extract the visual elements (e.g., bars, lines) and data from charts, and (ii) high-level tasks to acquire chart understanding and reasoning skills. |
Ahmed Masry; Parsa Kavehzadeh; Xuan Long Do; Enamul Hoque; Shafiq Joty; | arxiv-cs.CL | 2023-05-24 |
549 | Reasoning Over Hierarchical Question Decomposition Tree for Explainable Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose to leverage question decomposing for heterogeneous knowledge integration, by breaking down a complex question into simpler ones, and selecting the appropriate knowledge source for each sub-question. |
JIAJIE ZHANG et. al. | arxiv-cs.CL | 2023-05-24 |
550 | A Question Answering Framework for Decontextualizing User-facing Snippets from Scientific Documents Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we use language models to rewrite snippets from scientific documents to be read on their own. |
Benjamin Newman; Luca Soldaini; Raymond Fok; Arman Cohan; Kyle Lo; | arxiv-cs.CL | 2023-05-24 |
551 | Is Summary Useful or Not? An Extrinsic Human Evaluation of Text Summaries on Downstream Tasks Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We carefully design three different downstream tasks for extrinsic human evaluation of summaries, i.e., question answering, text classification and text similarity assessment. |
Xiao Pu; Mingqi Gao; Xiaojun Wan; | arxiv-cs.CL | 2023-05-24 |
552 | Interpretable By Design Visual Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we specifically focus on the problem of Visual Question Answering (VQA). |
Xingyu Fu; Ben Zhou; Sihao Chen; Mark Yatskar; Dan Roth; | arxiv-cs.CL | 2023-05-24 |
553 | Extracting Psychological Indicators Using Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we propose a method for extracting text spans that may indicate one of the BIG5 psychological traits using a question-answering task with examples that have no answer for the asked question. |
Luka Pavlović; | arxiv-cs.CL | 2023-05-24 |
554 | CAR: Conceptualization-Augmented Reasoner for Zero-Shot Commonsense Question Answering IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: However, two bottlenecks limit these approaches: the inherent incompleteness of CSKBs limits the semantic coverage of synthetic QA pairs, and the lack of human annotations makes the sampled negative examples potentially uninformative and contradictory. To tackle these limitations above, we propose Conceptualization-Augmented Reasoner (CAR), a zero-shot commonsense question-answering framework that fully leverages the power of conceptualization. |
WEIQI WANG et. al. | arxiv-cs.CL | 2023-05-24 |
555 | Measuring Faithful and Plausible Visual Grounding in VQA Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: To this end, we propose a new VG metric that captures if a model a) identifies question-relevant objects in the scene, and b) actually relies on the information contained in the relevant objects when producing its answer, i.e., if its visual grounding is both faithful and plausible. |
Daniel Reich; Felix Putze; Tanja Schultz; | arxiv-cs.CV | 2023-05-24 |
556 | Unlocking Temporal Question Answering for Large Language Models Using Code Execution Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Our preliminary experiments show that generating intermediate reasoning steps does not always boost the performance of complex temporal question-answering tasks. Therefore, we propose a novel framework that combines the extraction capability of LLMs and the logical reasoning capability of a Python solver to tackle this issue. |
XINGXUAN LI et. al. | arxiv-cs.CL | 2023-05-24 |
557 | NuScenes-QA: A Multi-modal Visual Question Answering Benchmark for Autonomous Driving Scenario Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We introduce a novel visual question answering (VQA) task in the context of autonomous driving, aiming to answer natural language questions based on street-view clues. |
Tianwen Qian; Jingjing Chen; Linhai Zhuo; Yang Jiao; Yu-Gang Jiang; | arxiv-cs.CV | 2023-05-24 |
558 | Chain-of-Questions Training with Latent Answers for Robust Multistep Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose Chain-of-Questions, a framework that trains a model to generate sub-questions and sub-answers one at a time by leveraging human annotated question decomposition meaning representation (QDMR). |
Wang Zhu; Jesse Thomason; Robin Jia; | arxiv-cs.CL | 2023-05-24 |
559 | Mitigating Temporal Misalignment By Discarding Outdated Facts Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: To mitigate the effects of temporal misalignment, we propose fact duration prediction: the task of predicting how long a given fact will remain true. |
Michael J. Q. Zhang; Eunsol Choi; | arxiv-cs.CL | 2023-05-24 |
560 | InteractiveIE: Towards Assessing The Strength of Human-AI Collaboration in Improving The Performance of Information Extraction Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Since the purpose of question answering intersect with the goal of information extraction, we use automatic question generation to induce template slots from the documents and investigate how a tiny amount of a proxy human-supervision on-the-fly (termed as InteractiveIE) can further boost the performance. |
ISHANI MONDAL et. al. | arxiv-cs.CL | 2023-05-23 |
561 | Exploring Contrast Consistency of Open-Domain Question Answering Systems on Minimally Edited Questions Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we collect minimally edited questions as challenging contrast sets to evaluate OpenQA models. |
Zhihan Zhang; Wenhao Yu; Zheng Ning; Mingxuan Ju; Meng Jiang; | arxiv-cs.CL | 2023-05-23 |
562 | Asking Clarification Questions to Handle Ambiguity in Open-Domain QA Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Instead, we propose to ask a clarification question, where the user’s response will help identify the interpretation that best aligns with the user’s intention. |
DONGRYEOL LEE et. al. | arxiv-cs.CL | 2023-05-23 |
563 | Few-shot Unified Question Answering: Tuning Models or Prompts? Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The paper provides an exhaustive analysis of their applicability using 16 QA datasets, revealing that prompt tuning can perform as well as model tuning in a few-shot setting with a good initialization. |
Srijan Bansal; Semih Yavuz; Bo Pang; Meghana Bhat; Yingbo Zhou; | arxiv-cs.CL | 2023-05-23 |
564 | IfQA: A Dataset for Open-domain Question Answering Under Counterfactual Presuppositions Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Although counterfactual reasoning is a fundamental aspect of intelligence, the lack of large-scale counterfactual open-domain question-answering (QA) benchmarks makes it difficult to evaluate and improve models on this ability. To address this void, we introduce the first such dataset, named IfQA, where each question is based on a counterfactual presupposition via an if clause. |
Wenhao Yu; Meng Jiang; Peter Clark; Ashish Sabharwal; | arxiv-cs.CL | 2023-05-23 |
565 | Getting MoRE Out of Mixture of Language Model Reasoning Experts Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We provide empirical evidence that state-of-the-art LLMs suffer from poor generalizability on reasoning types beyond those seen in the prompt. To remedy this, we propose a Mixture-of-Reasoning-Experts (MoRE) framework that ensembles diverse specialized language models. |
Chenglei Si; Weijia Shi; Chen Zhao; Luke Zettlemoyer; Jordan Boyd-Graber; | arxiv-cs.CL | 2023-05-23 |
566 | Make A Choice! Knowledge Base Question Answering with In-Context Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we present McL-KBQA, a framework that incorporates the few-shot ability of LLM into the KBQA method via ICL-based multiple choice and then improves the effectiveness of the QA tasks. |
Chuanyuan Tan; Yuehe Chen; Wenbiao Shao; Wenliang Chen; | arxiv-cs.CL | 2023-05-23 |
567 | Evaluating and Modeling Attribution for Cross-Lingual Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We find that Natural Language Inference models and PaLM 2 fine-tuned on a very small amount of attribution data can accurately detect attribution. Based on these models, we improve the attribution level of a cross-lingual question-answering system. |
BENJAMIN MULLER et. al. | arxiv-cs.CL | 2023-05-23 |
568 | RET-LLM: Towards A General Read-Write Memory for Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: However, existing LLMs lack a dedicated memory unit, limiting their ability to explicitly store and retrieve knowledge for various tasks. In this paper, we propose RET-LLM a novel framework that equips LLMs with a general write-read memory unit, allowing them to extract, store, and recall knowledge from the text as needed for task performance. |
Ali Modarressi; Ayyoob Imani; Mohsen Fayyaz; Hinrich Schütze; | arxiv-cs.CL | 2023-05-23 |
569 | What Else Do I Need to Know? The Effect of Background Information on Users’ Reliance on QA Systems Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we study how users interact with QA systems in the absence of sufficient information to assess their predictions. |
NAVITA GOYAL et. al. | arxiv-cs.CL | 2023-05-23 |
570 | Selectively Answering Ambiguous Questions Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We investigate question answering from this perspective, focusing on answering a subset of questions with a high degree of accuracy, from a set of questions in which many are inherently ambiguous. |
JEREMY R. COLE et. al. | arxiv-cs.CL | 2023-05-23 |
571 | OpenPI2.0: An Improved Dataset for Entity Tracking in Texts Related Papers Related Patents Related Grants Related Venues Related Experts Related Code |