Information Retrieval Papers of the Week

Through controlled interventions, we identify the item-mean component as a contributor to exposure collapse. Accordingly, we propose two reward corrections: per-item centering removes each item's estimated mean score, while per-item standardization further rescales the residual using its estimated standard deviation.

Scientific names increasingly connect papers from different research topics, leaving readers to recover a paper's identity from context. We study this convergence in 564,861 AI-related arXiv records.

However, existing methods typically rely on a single fixed teacher, remain constrained by the teacher knowledge ceiling, and indiscriminately distill teacher-generated trajectories without assessing their actual utility for downstream recommendation. To address these limitations, we propose MUSE (Multi-Teacher Utility-guided Selection with Self-Exploration), an adaptive reasoning distillation framework that jointly improves reasoning generation and reasoning utilization.

Here, we present PROTAC-DB 4.0, an expanded knowledgebase covering major targeted degradation and induced-proximity technologies.

We present DualClusterNet, a causal sequential recommender that composes two population-shared prototype dictionaries.

Existing LLM agents fail to ground observation items or suffer from search-space explosion. We propose OSGR, a two-stage framework that factorizes this search into offline symbolic concept deduction and online Relation-Conditioned Grounding.

This ``one-size-fits-all'' strategy often leads to suboptimal representation learning due to over-thinking in simple histories or under-thinking in complex ones. To address this issue, we propose DESRec, a deliberate latent reasoning framework that performs personalized latent reasoning to learn more informative reasoning states and enhance user modeling for sequential recommendation.

A hidden requirement can be found only by proposing books and inferring it from the user's accept or reject verdicts.

In this paper, we formulate page-centric Visual Document Retrieval (VDR) with pages as the fundamental indexing units and document context available for assessing page relevance.

We formulate re-ranking depth as a query-specific property and study whether it can be predicted a priori from first-stage retrieval characteristics. Through a large-scale analysis, we find that most standard query performance prediction (QPP) methods are ineffective for this task.

A key challenge is that teacher trajectories for agentic supervised finetuning are noisy, mixing critical reasoning and action steps with redundant or failed attempts. To address this, we introduce counterfactual credit reweighting, a fine-grained credit assignment method that weights individual reasoning and action steps by their counterfactual contribution to the final answer.

Despite extensive research, no universally accepted definition or standardised framework exists for evaluating the quality of consumer health information. This narrative review examines how consumer health information quality is defined and evaluated across web-based and LLM-generated environments, and assesses the role of search engine ranking mechanisms in shaping the visibility and accessibility of such information.

This study investigates the effectiveness of large pre-trained language models (LLMs) for knowledge entity relation extraction (KERE) from academic papers.

We introduce CORE, a training-free harness that combines coarse-to-fine search with context management.

In this work, we introduce Factorized MLLM Embeddings (FactEmbed), which decouples compositional query comprehension from building discriminative embeddings.

Semantic retrieval models aim to match documents to a query's "meaning", yet it remains unclear whether they successfully encode temporal relations between events in their ranking mechanisms.

Other artifacts--ontology, graph, wiki, timeline, mind map, memory--pay off in deployment (governance, integration, onboarding, temporal orientation, continuity) where accuracy benchmarks cannot see them. We describe RAGFlow's pipeline and harness (open source at this https URL), which turns the loop into five disciplined stations and keeps the context entering the model the smallest sufficient set; together they form an agent-native database: a store that hands the agent compiled, governed context instead of a ranked list of passages.

We propose a simple method that prepends trainable [DUMP] tokens to the input during embedding model training.