Information Retrieval and Search Behavior

Últimos artículos

• Found but Not Read: When Extracted Text Closes the Retrieval-Reading Gap in Document Vision-Language Models

  Qingtao Xia, Siyao Cheng, Jiahua Bao, Jiaxing Du, Jie Liu · 5 de octubre de 2026

  Retrieval-augmented document question answering assumes that once the right page is found, a vision-language model (VLM) can read it. We show that this assumption often fails, leaving a retrieval-reading gap: evidence found but not used. A paired protocol isolates this gap by comparing answers from …

• Source Preference in the Wild: How LLM Agents Favor Items by Source, and How to Reduce It

  Jonghyun Song, Haewon Park, Jeonghoon Shim, Woojung Song, Yohan Jo · 5 de octubre de 2026

  As LLM agents decide on users' behalf which product to buy, which hotel to book, or which paper to cite, a preference for items from certain sources (the sites or services they come from) shapes what users receive and which sources are selected. We study source preference in end-to-end search with 1…

• Query-aware routing for Cross-lingual performance gains in Encoders

  Akshay Jain, Edward Kim · 5 de octubre de 2026

  Multilingual encoders can exhibit reduced retrieval effectiveness when queries and relevant documents differ in language, despite strong same-language performance. We investigate whether Finnish and Swedish cross-lingual retrieval can improve while preserving an encoder's existing same-language perf…

• MRVQ: One Resident Index for Dimension- and Rate-Elastic Vector Search

  Sean Culatana, Shang-En Huang, Kang Li · 5 de octubre de 2026

  Dense-retrieval services must switch among embedding-prefix dimensions and index bit rates as latency, quality, and memory budgets change. Tuning a quantizer separately for each rate gives the best quality, but the retrieval tier then holds several code streams and quantizer states at once. We intro…

• AMBER: Multi-View Adaptive Budget Allocation for Listwise Vision-Language Reranking

  Wenteng Chen, Jiachen Zhu, Rong Shan, Tianyi Xu, Yuxiang Chen, Congmin Zheng, Teng Wang, Junjie Wu, Weiwen Liu, Changwang Zhang, Weinan Zhang, Jun Wang, Jianghao Lin · 5 de octubre de 2026

  Vision-language models (VLMs) are powerful listwise rerankers for multimodal retrieval, but high inference costs restrict them to evaluating small local candidate views. Existing multi-call strategies rely on fixed schedules, wasting expensive VLM calls on uninformative candidate pairs and easy quer…

• How To Train Your World Model: Fine-tuning vs RAG for LM-based World Modeling

  Dhananjay Ashok, Shantanu Agarwal, Vivek Datla, Jonathan May, Alfy Samuel · 5 de octubre de 2026

  World models (WMs) simulate the transition dynamics of environments, enabling agents to plan over the consequences of their actions. In text-based environments, fine-tuning a Language Model (LM) to serve as a WM has emerged as a dominant paradigm. However, despite the widespread success of non-param…

• RPTune: Learned Context Curation for LLM Catalog Search

  Chuxuan Hu, Hejie Cui, Norman Huang, Shubham Kumar Bharti, Wang-Chiew Tan, Sercan \"O. Ar{\i}k · 2 de octubre de 2026

  For small merchant businesses (SMBs) whose catalogs fit within a long-context LLM, full-catalog prompting offers a compelling alternative to multi-stage retrieval designed primarily for large marketplaces with millions of items. However, fitting the full catalog into the context window does not ensu…

• On-Device Commercial Intent Retrieval Under Size, Latency, and Privacy Constraints: A 3 MiB Retrieval System with Typed Egress Boundaries

  Hyojung Han · 2 de octubre de 2026

  We study commercial intent inference that runs entirely on the user's device, under three constraints frozen before the work began: the downloaded payload under 3 MiB, Tier-0 inference under 20 ms at p95, and no raw text, content embedding, or stable identifier leaving the device. Under them we buil…

• A Matryoshka Hierarchical RAG for Efficient Multi-Hop Question Answering

  Gianluca Bonifazi, Christopher Buratti, Michele Marchetti, Federica Parlapiano, Giulia Quaglieri, Davide Traini, Domenico Ursino, Luca Virgili · 2 de octubre de 2026

  Retrieval-Augmented Generation (RAG) systems for multi-hop Question Answering (QA) must balance retrieval quality with computational cost. This cost is incurred during indexing time, through the use of expensive Knowledge Graphs (KGs) or Large Language Models (LLMs) to generate summaries, or during …

• AgSpec: Pushing the Limits of Retrieval-Based Speculative Decoding in Coding Agent Pipelines

  Sumin Lee, Sukmin Cho, Suengjae Lim, Youngjin Kwon · 2 de octubre de 2026

  Retrieval-based speculative decoding (SD) drafts tokens by copying continuations from existing text, which suits coding agents that repeatedly reproduce code, logs, and earlier attempts. Yet existing methods fall short in agent pipelines: much of the reusable text is missing from their corpora or st…

• Mapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoning

  Meghana Sunil, Shravya V, Shravan Venkatraman, Joe Dhanith PR · 2 de octubre de 2026

  Large Language Models (LLMs) have demonstrated remarkable fluency across many tasks but remain limited by their static, parameter bound knowledge and their susceptibility to hallucinating information. Retrieval Augmented Generation (RAG) addresses these issues by incorporating external retrieval int…

• HHR: Hierarchical Hash Retrieval for Efficient LLM Generation

  Lianjun Liu, Tiantian Zheng, You Huang, Weiqi Yan, Mingte Qiu, Huazhong Liu, Xiaofeng Zhu, Yunshan Zhong · 2 de octubre de 2026

  Efficient long-context inference is essential for large language models (LLMs), yet it poses a severe computational bottleneck. Hash-based retrieval offers an efficient alternative by encoding queries and keys into binary codes and using Hamming distance for key selection. However, this leads to a c…

• What Should an Agent Remember? Disentangling Retention from Retrieval in Bounded-Memory Evaluation

  Juli Huang · 2 de octubre de 2026

  A persistent agent must decide both what to retain as information arrives and what to surface once a query appears, yet memory evaluations can confound these decisions by comparing methods that differ in both retention and selection. We build a streaming-recall benchmark crossing retention and selec…

• IROH: Insightful Ranking Of Humor using Multi-Stage Hybrid Retrieval with Rationale-Distilled LLM Judges for JOKER 2026 Track Task 1 English

  Ana-Maria Luisa Mocanu, Sebastian Mocanu, Ciprian-Octavian Truica, Elena-Simona Apostol · 1 de octubre de 2026

  Our team, VANGUARD, presents IROH (Insightful Ranking of Humor), a three-stage retrieval system for JOKER Task 1 English at CLEF 2026, achieving first place on the leaderboard with 0.6347 MAP. Our pipeline combines hybrid sparse-dense retrieval, cross-encoder reranking, and a LoRA-adapted Large Lang…

• Effective Dense Retrieval using Only In-Context Examples

  Nour Jedidi, Abdul Basit Ali, Hang Li, Jimmy Lin · 1 de octubre de 2026

  Turning decoder-only large language models (LLMs) into strong dense retrievers typically requires some form of retriever training. In this paper, we ask whether LLMs can instead be prompted to produce effective representations for dense retrieval given only a few in-context examples. To answer this,…

• MERGE: Multi-LLM Ensemble for Retrieval via Generative Enrichment

  Tzu-I Ho, Yung-Yu Shih, Shang-Yu Su, Dongzhe Wang, Yun-Nung Chen · 1 de octubre de 2026

  Large Language Models (LLMs) are increasingly used to enrich user queries in information retrieval (IR) so that a standard retriever such as BM25 can bridge vocabulary gaps with the target corpus. Any single LLM, however, is limited by its training data and architectural biases, and its enrichment b…

• Bridging Semantic Gaps in RAG through Generated Context Knowledge Fusion

  Xinkai Du, Chao Lv, Yalin Sun, Quanjie Han, Lei Yao, Maosong Sun · 1 de octubre de 2026

  Retrieval-Augmented Generation has established itself as a fundamental framework in natural language processing, seamlessly integrating information retrieval with the generative capabilities of large language models. However, this process is fundamentally constrained by a critical challenge: semanti…

• Traverse: Learning When to Remember, Reset, and Redirect for Long-Horizon Web Search

  Jingyuan Ma, Lynx Aster, He Zhang, Siyao Song, Weijie Yuan, Zhe Zhang, Kai Jia, Zhifang Sui · 1 de octubre de 2026

  Long-horizon information-seeking agents often accumulate noisy or misleading context, causing early mistakes to persist and making recovery increasingly difficult. We introduce an autonomous search harness in which the agent manages its own search process through three states: Rubric, Answer, and Ve…

• Grounded Revision vs. Prior Injection: Probing Retrieval-Augmented Patent Claim Amendment

  Josepha Michiko Leo, Hyun-seok Min, Yehoon Jang, Irvan Zidny, Jin-Woo Chung, Sungchul Choi · 1 de octubre de 2026

  Retrieval-augmented generation is widely used in professional writing, yet whether retrieval grounds revision or merely injects templates is rarely tested where "correct" has a definable meaning. Patent claim amendment supplies that signal: the examiner names the attacked limitation and cites prior …

• Beyond the Context Window: An Adaptive Entropy-Based Routing Framework for Hybrid Retrieval and Long-Context Language Models

  Isaac Olufadewa, Miracle Adesina, Ezekiel Oladejo, Owen Adeniyi, Fadare Fadekemi, Olamide Oso, Uthman Babatunde, Matthew Olawoyin · 1 de octubre de 2026

  Modern large language models now support context windows of more than one million tokens, which has raised the question of whether retrieval-augmented generation (RAG) is still necessary. Pure long-context (LC) processing is expensive and is known to under-attend to information placed in the middle …

• Sieve and Sage: Efficient Distraction Filtering for Reliable RALM Abstention

  Jongbin Won, Sung Geun An, Jay-yoon Lee · 1 de octubre de 2026

  Just as Socrates recognized the limits of his own knowledge, Retrieval-Augmented Language Models (RALMs) should learn to abstain when the retrieved evidence cannot support a reliable response. Existing approaches largely rely on monolithic LLMs to handle heterogeneous retrieval failures in a single …

• Instruction Retrieval at Inference Time for Small Language Models

  Kenan Alkiek, David Jurgens, Vinod Vydiswaran · 1 de octubre de 2026

  The facts a language model stores are tied to its parameter count, so small models that fit on edge devices fail on expert problems, which need specialized knowledge and follow multi-step procedures. Fine-tuning for a specific domain or task writes the knowledge into the parameters but must be repea…

• TRACE: Trajectory Selection for Parallel Scaling of Search Agents

  Qisheng Zhou, Zhen Xiong, Qiaoyu Tan · 1 de octubre de 2026

  Parallel search may generate a correct answer that final-answer voting fails to select. We formulate this consolidation stage as trajectory selection and introduce TRACE (Trajectory Ranking with Aggregated Cross-Rollout Evidence), a lightweight learned selector that ranks completed trajectories usin…

• RAGScope: A Leakage-Controlled, Cost-Aware Evidence-Gating Protocol for RAG Hallucination Triage

  Zeming Liu, Qibai Chen, Jingtao Zhang, Hang Lyu · 1 de octubre de 2026

  Retrieval-augmented generation (RAG) systems need inexpensive ways to route generated answers: accept low-risk outputs, review uncertain ones, and reserve strong verifiers for the expensive tail. We present RAGScope, a leakage-controlled protocol for evaluating local evidence gates that use only the…

• SkillSeek: Revisiting Agent Skill Retrieval at Marketplace Scale

  Guanqun Yang, Wenlong Zhang, Tian Shi, Ping Wang · 1 de octubre de 2026

  Anthropic's Agent Skills package reusable procedural know-how for an LLM agent into SKILL.md directories, and open-source aggregations have grown past 230,000 skills, making selection rather than authoring the bottleneck. The standing answer in the literature outsources selection to the agent itself…