Knowledge Retrieval in Language Models

Latest papers

35 papers7 papers in the last four weeks, down 22% on the four weeks before. 0.0% of all new papers.

Who Asks, Who Answers: Linear Attention Builds the Query in Hybrid Language Models
Nov 1, 2026Wenqi Zeng, Chen Feng, YuAng ChenKnowledge Retrieval in Language Models Hybrid Language Models
The Hong Kong University of Science and Technology · The Hong Kong Polytechnic University · The Chinese University of Hong Kong
Less but Sufficient: Relation Knowledge Selects Compact Knowledge-Graph Contexts, and What External Checks Can and Cannot Catch
Nov 1, 2026Seunghui Jwa, Minsu Oh, Sangwoo Hong +1Knowledge Graph Question Answering Knowledge Retrieval in Language Models
Department of Artificial Intelligence, Jeju National University · Department of Computer Science and Engineering, Konkuk University
Cross-Prompt Reuse of Entity-Replacement Responses
Oct 30, 2026Jinkun Chen, Xuemin Yu, Sijia Han +1LLM Prompting Factual Knowledge in Language Models
Dalhousie University Halifax, Canada · Meta
ImplicitHop: Evaluating knowledge integration across context and memory
Oct 30, 2026Alexander Detkov, Dashiel Karish, Matthew Oleynikov +1Knowledge Retrieval in Language Models Language Model Reasoning Evaluation
California Institute of Technology
TeamGym: A Gym for Team Decision-Making by AI Agents with Distributed Information
Oct 27, 2026Chanwoo Park, Jaywoong Jeong, Zachary Wojtowicz +4Knowledge Retrieval in Language Models Multi-Agent Collaboration
MIT · KAIST · UT Austin +1
Retriever-Free Retrieval: Navigating Documents with Decision Models
Oct 26, 2026Chao Wan, Paul Jünger, Beixi Du +3Knowledge Retrieval in Language Models Information Retrieval
Department of Computer Science, Cornell University, New York, USA · ASAPP, New York, USA
Rethinking Retrieval in the Long-Context Era: Training-Free Semantic Trees for Adaptive Context Construction
Oct 25, 2026Zhe Xu, Tianhao Liao, Zhenqing Ling +3Long-Context Retrieval Knowledge Retrieval in Language Models
Sun Yat-sen University · Alibaba Group
ColdDDI: Evaluating Knowledge Utilization in Cold-Start Drug-Drug Interaction Prediction
Oct 4, 2026Jiheng Liang, Chen Zhao, Di Wu +4Knowledge Retrieval in Language Models Drug-Drug Interaction Prediction
Data Science, William & Mary · Computer Science, Baylor University · Southwest University +2
Learning a Fact Is Not Learning How to Retrieve It
Oct 2, 2026Chaemin Jang, Jihee Kim, Dongman LeeKnowledge Retrieval in Language Models Factual Knowledge in Language Models
Korea Advanced Institute of Science and Technology (KAIST)
MedKIT: Evaluating Knowledge Integration and Generalization in Large Language Models
Sep 29, 2026Lukas Thede, Yash Kumar Atri, David Chen +4Continual Learning for LLMs Knowledge Retrieval in Language Models
University of Tübingen, Tübingen AI Center · Helmholtz Munich · Munich Center for Machine Learning (MCML) +4
Learning to Retrieve Missing Evidence for Long-Term Memory QA
Sep 29, 2026Yi-Xuan Deng, Yi Zhang, Wei Liu +2RL for IR Evidence Retrieval
Tsinghua University
What Should Data Teach? Moving Bottlenecks Across Circuit, Store, and Use
Sep 26, 2026Yixiao Chen, Ke Cheng, Jiangtao Guan +5Knowledge Retrieval in Language Models Language Model Pretraining
AI Data, Tencent · Harvard University · AMS, Tencent
The Key Handoff: Retrieval in Hybrid Language Models
Sep 26, 2026Kaan Kale, Oguzhan Baser, Sriram VishwanathKnowledge Retrieval in Language Models Hybrid Language Models
Georgia Institute of Technology, USA · University of Texas at Austin, USA
Memory vs. Context? Influential Factors of Factual Recall in Language Models
Sep 21, 2026Guilhem Fouilhé, Nicholas Asher, Philippe MullerPrompt Sensitivity Memorization in Language Models
IRIT ANITI · IRIT CNRS · IRIT Université de Toulouse
Parameter-Efficient Retrievers for Polish and European Languages
Sep 11, 2026Sławomir Dadas, Rafał Poświata, Małgorzata Grębowiec +1Multilingual IR Information Retrieval
National Information Processing Institute al. Niepodległości 188b, 00-608 Warsaw, Poland
From Parameters to Answers: How LLMs Retrieve and Use Their Internal Knowledge
Sep 10, 2026Wenkang Wei, Yuan Fang, Renhe Jiang +2Knowledge Retrieval in Language Models LLM Interpretability
University of Science and Technology of China Hefei, China · Singapore Management University Singapore, Singapore · The University of Tokyo Tokyo, Japan +1
GEM: A Generative Embedding Model Bridging Reasoning and Retrieval
Aug 13, 2026Zhili Shen, Craig MacdonaldText Embedding Models Knowledge Retrieval in Language Models
University of Glasgow
Co-LMLM: Continuous-Query Limited Memory Language Models
Jul 8, 2026Yair Feldman, Linxi Zhao, Nathan Godey +5Language Model Pretraining Memory-Augmented Language Models
Department of Computer Science Cornell University
When Should LLMs Search? Counterfactual Supervision for Search Routing
Jul 7, 2026Minho KimKnowledge Augmentation for Language Models LLM Routing
1Sangmyung University · 2DMTLABS.
Can Language Models Actually Retrieve In-Context? Drowning in Documents at Million Token Scale
Jul 1, 2026Siddharth Gollapudi, Nilesh Gupta, Prasann Singhal +1In-Context Retrieval Length Generalization
UC Berkeley · UT Austin
KARLA: Knowledge-base Augmented Retrieval for Language Models
Jun 25, 2026Francois Crespin, Fabian M. Suchanek, Nils HolzenbergerRetrieval-Augmented Generation LLM Grounding
IP Paris, LTCI · Télécom Paris · Institut Polytechnique de Paris, France
Self-Augmenting Retrieval for Diffusion Language Models
Jun 4, 2026Paul Jünger, Justin Lovelace, Linxi Zhao +2Diffusion Language Models Retrieval-Augmented Generation
Department of Computer Science, Cornell University.
Benchmarking the Personalization Capabilities of Large Language Models
May 23, 2026Ashutosh Srivastava, Siddharth Yedlapati, Vinay Aggarwal +4Knowledge Retrieval in Language Models Language Model Generation Evaluation
Adobe Media & Data Science Research
Predictable Confabulations: Factual Recall by LLMs Scales with Model Size and Topic Frequency
May 18, 2026Matthew L. Smith, Jonathan P. Shock, Samuel T. Segun +2LLM Evaluation Language Model Scaling Laws
International Development Research Centre Canada · University of Cape Town South Africa · Global Center on AI Governance Canada +2
MeMo: Memory as a Model
May 14, 2026Ryan Wei Heng Quek, Sanghyuk Lee, Alfred Wei Lun Leong +6Retrieval-Augmented Generation Memory-Augmented Language Models
Institute of Data Science, National University of Singapore, Singapore · Integrative Sciences and Engineering Programme, NUSGS, Singapore · Agency for Science, Technology, Research (A*STAR), Singapore +6
SearchSkill: Teaching LLMs to Use Search Tools with Evolving Skill Banks
May 9, 2026Jinchao Hu, Meizhi Zhong, Kehai Chen +1Tool-Augmented Language Model Agents Agentic Search
School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen · Independent Researcher Shenzhen / Beijing, China
DiffRetriever: Parallel Representative Tokens for Retrieval with Diffusion Language Models
May 8, 2026Shuai Wang, Yu Yin, Shengyao Zhuang +2Multi-Vector Retrieval Diffusion Language Models
The University of Queensland, Brisbane, QLD, Australia · CSIRO
Evolve: A Persistent Knowledge Lifecycle for Small Language Models
Apr 25, 2026Dikran HovagimianKnowledge Augmentation for Language Models Knowledge-Intensive QA
Independent Researcher
EngramaBench: Evaluating Long-Term Conversational Memory with Structured Graph Retrieval
Apr 23, 2026Julian AcunaLong-Term Conversational Memory LLM Evaluation
To Memorize or to Retrieve: Scaling the Interaction Between Pretraining and Retrieval
Apr 1, 2026Karan Singh, Michael Yu, Varun Gangal +4Retrieval-Augmented Generation Knowledge Retrieval in Language Models
Stanford University · †DegenAI Labs · Independent Researcher +3

Nov 1, 2026J/K move · Enter open · S save

Who Asks, Who Answers: Linear Attention Builds the Query in Hybrid Language Models

Wenqi Zeng, Chen Feng, YuAng Chen

The Hong Kong University of Science and Technology · The Hong Kong Polytechnic University · The Chinese University of Hong Kong

Knowledge Retrieval in Language Models Hybrid Language Models Linear Attention Mechanistic Interpretability

Open paper AskPDF arXiv

Hybrid language models interleave linear-attention layers with a small number of softmax-attention layers. Prior work largely attributes in-context retrieval to softmax attention, treating linear attention primarily as a mechanism for compressing past context. We revisit this division of labor and show that linear attention plays a direct role in retrieval by constructing the query used by softmax attention. Studying Qwen3.5 (Gated DeltaNet) and Granite4.0 (Mamba-2), we identify an Encode--Address circuit. An early Encode block preserves token identity, while an Address block constructs the final-position representation from which a softmax reader forms its attention query. Transplanting this representation between prompts with different queried keys redirects retrieval in 0.97--0.99 of cases. The Address block's recurrent state carries the retrieval target, and its computation transfers across architectures: replacing Granite's Address block with Qwen's restores retrieval accuracy to 0.92--0.94 without updating either model's weights. Across six Qwen3.5 models, Address computation becomes distributed at larger scales over a chain of blocks, each guiding a successive reader, as the query no longer passes from one reader to the next through attention. These findings reveal a division of labor in hybrid retrieval: linear attention constructs the query, while softmax attention performs the lookup. Code is available at https://github.com/yuang-chen/LinearQuery