Query Expansion

Follow this topic Ask about this topic

Query expansion studies how to enrich a search query so retrieval systems can find relevant documents despite vocabulary mismatch or underspecified intent. Methods range from lexical expansion and relevance feedback to LLM-generated rewrites or pseudo-documents, with newer approaches grounding terms in retrieved passages, corpus statistics, or retrieval feedback and coordinating dense and sparse retrievers. Systems are commonly evaluated on BEIR and TREC collections using ranking metrics such as nDCG and recall, as well as in domain-specific search and retrieval-augmented generation. Gains are often useful but vary by corpus and retriever: unsupported generated terms can cause drift, while strong rerankers or sparse models may leave limited room for improvement, making accuracy, faithfulness, and inference cost ongoing trade-offs.

Latest papers

24 papers4 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Tracing and Taming Hallucinated Terms via Subsequence-Association Filtering and Breadth-Aware Selection for LLM Query Expansion
Oct 9, 2026Amit Kumar Jaiswal, Sagar Uprety, Prayag TiwariQuery Expansion Information Retrieval
Indian Institute of Technology (BHU), Varanasi, India · University College London, London, UK · Halmstad University, Halmstad, Sweden
Towards Explaining Query Expansion Performance in Information Retrieval
Oct 7, 2026Sourav Saha, Aditya Dutta, Soumajit Pramanik +1Information Retrieval Query Expansion
Indian Statistical Institute, Kolkata, India · IIT Bombay, Bombay, India · IIT Bhilai, Chhattisgarh, India
Benchmarking Literature Retrieval for a Model Organism: A Dictyostelium Case Study
Oct 2, 2026Yun Wang, Gad Shaulsky, Tomaž Curk +1Scientific Document Retrieval Biomedical IR
University of Ljubljana, Faculty of Computer and Information Science, Večna pot 113, 1000 Ljubljana, Slovenia · Department of Molecular and Human Genetics, Baylor College of Medicine, Baylor Plaza, Houston, TX 77030, USA
Generated Query Expansion Still Helps Strong Sparse Retrieval: A Controlled Study with SPLADE-v3
Sep 29, 2026Ryan C. Barron, Cade W. Trotter, Maksim E. Eren +3Learned Sparse Retrieval Lexical Retrieval
Computational Intelligence & Modeling, Los Alamos National Laboratory, Los Alamos, New Mexico, USA. · Modeling and Observations of Earth Systems, Los Alamos National Laboratory, Los Alamos, New Mexico, USA. · Fluid Dynamics and Solid Mechanics, Los Alamos National Laboratory, Los Alamos, New Mexico, USA. +2
Staged Linguistic Seeding: Grounded Query Expansion for Verified-Unit QA in AI Contact Centers
Sep 1, 2026Hyeonseop Yoon, Jeong-Eun ParkCustomer Support Automation Question Answering
Independent Researcher Seoul, South Korea
DEPT: Document Embedding Preservation Tuning for Unified Query Expansion and Retrieval
Aug 18, 2026Jingyuan Wang, Richong Zhang, Zhijie Nie +2Dense Retrieval Query Expansion
Beihang University, China
Query Expansion Should Be Coordinated: Dense Expands, Sparse Anchors
Aug 16, 2026Chunran ZhangRetrieval-Augmented Generation RAG Evaluation
School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu, China
Retrieval Augmented Biomedical Question Answering with Weak Question Recovery and Neural Reranking for BioASQ Task 14b
Aug 2, 2026Xueying Zhao, Lee Mai, Balaji AnandganeshRetrieval-Augmented Generation Learning to Rank
Georgia Institute of Technology, North Ave NW, Atlanta, GA 30332
CeQe: Grounding Lexical Retrieval in Semantic Evidence
Aug 1, 2026Adam Kahirov, Umesh Deshpande, Swaminathan SundararamanLexical Retrieval Information Retrieval
IBM Research
Improving Item Discoverability in e-Commerce Search via Related Intent Generation
Jul 29, 2026Ji Xin, Xiao Xiao, Ishan Bhatt +6E-Commerce Search Information Retrieval
Instacart Toronto, Canada · Instacart San Diego, USA · Instacart San Francisco, USA +1
Beyond the Reranker: Do RAG Retrieval Enhancements Help Once a Strong Reranker Is Present?
Jun 14, 2026Sadanand Singh, Allam Reddy, Manan ChopraCross-Encoder Reranking Learning to Rank
Cascade Research
ADORE: Iterative Query Expansion with Retrieval-Grounded Relevance Feedback
Jun 11, 2026Amin Bigdeli, Negar Arabzadeh, Radin Hamidi Rad +3Information Retrieval Query Expansion
University of Waterloo · University of California, Berkeley · Mila – Quebec AI Institute +1
STORM: Stepwise Token Optimization with Reward-Guided Beam Search
Jun 9, 2026Arthur Satouf, Giulio D'Erasmo, Yuxuan Zong +3Language Model Decoding Lexical Retrieval
MILA – Quebec AI Institute & ILLS, Canada · 5Sapienza, University of Rome, Italy · 4Sorbonne Université & ISIR & CNRS, France +2
MARQUIS: A Three-Stage Pipeline for Video Retrieval-Augmented Generation
May 17, 2026Debashish Chakraborty, Dengjia Zhang, Jialiang Jin +7Multimodal RAG Retrieval-Augmented Generation
Johns Hopkins University · Human Language Technology Center of Excellence
Superintelligent Retrieval Agent: The Next Frontier of Agentic Retrieval
May 7, 2026Zeyu Yang, Qi Ma, Jason Chen +1Agentic Retrieval Information Retrieval
Meta Superintelligence Labs · Rice University · Work done at Meta
Open-SAT: LLM-Guided Query Embedding Refinement for Open-Vocabulary Object Retrieval in Satellite Imagery
May 6, 2026Md Adnan Arefeen, Biplob Debnath, Ravi K. Rajendran +2Remote Sensing Image Understanding Image-Text Retrieval
NEC Laboratories America Princeton, NJ, USA
AdaQE-CG: Adaptive Query Expansion for Web-Scale Generative AI Model and Data Card Generation
Mar 16, 2026Haoxuan Zhang, Ruochi Li, Zhenni Liang +7Document Information Extraction Generative AI Evaluation
Compute Allocation for Reasoning-Intensive Retrieval Agents
Mar 15, 2026Sreeja Apparaju, Nilesh GuptaInference-Time Compute Allocation Information Retrieval
LITTA: Late-Interaction and Test-Time Alignment for Visually-Grounded Multimodal Retrieval
Mar 10, 2026Seonok KimMultimodal IR Visual Document Retrieval
Mazelone
Seeing Through Words: Controlling Visual Retrieval Quality with Language Models
Feb 24, 2026Jianglin Lu, Simon Jenni, Kushal Kafle +3Vision-Language Retrieval Image Retrieval
Adobe Research · Northeastern University
MTRACE: Multilingual Retrieval-Augmented Generation for Temporally Diverse Text Corpora
Dec 14, 2025Souhail Bakkali, Anthony MudetRetrieval-Augmented Generation Multilingual IR
Univ Rennes, CNRS, IRISA - UMR 6074, Rennes, France · L3i-lab, La Rochelle Universit´e, France
Rethinking On-policy Optimization for Query Augmentation
Oct 20, 2025Zhichao Xu, Shengyao Zhuang, Xueguang Ma +6RL for Language Models LLM Prompting
University of Utah · 2The University of Queensland · University of Waterloo +5
Chain of Retrieval: Multi-Aspect Iterative Search Expansion and Post-Order Search Aggregation for Full Paper Retrieval
Jul 14, 2025Sangwoo Park, Jinheon Baek, Soyeong Jeong +1Scientific Document Retrieval Information Retrieval
KAIST
LLM-powered Query Expansion for Enhancing Boundary Prediction in Language-driven Action Localization
May 30, 2025Zirui Shang, Xinxiao Wu, Shuo YangTemporal Action Localization Query Expansion
Beijing Key Laboratory of Intelligent Information Technology, School of Computer Science & Technology, Beijing Institute of Technology, China. · Guangdong Laboratory of Machine Perception and Intelligent Computing, Shenzhen MSU-BIT University, China.

Oct 9, 2026J/K move · Enter open · S save

Tracing and Taming Hallucinated Terms via Subsequence-Association Filtering and Breadth-Aware Selection for LLM Query Expansion

Amit Kumar Jaiswal, Sagar Uprety, Prayag Tiwari

Indian Institute of Technology (BHU), Varanasi, India · University College London, London, UK · Halmstad University, Halmstad, Sweden

Query Expansion Information Retrieval LLM Hallucination Mitigation

Open paper AskPDF arXiv

Large language models (LLMs) are now a standard source of query expansion terms but they hallucinate. They inject non existent entities and off-topic terms that add ranking noise and can hurt strong retrievers. Existing remedies such as corpus grounding, mutual verification and preference alignment treat hallucinated terms as an undifferentiated nuisance to be filtered by agreement heuristics, without a mechanistic account of why a given term appears or a principled criterion for how many terms to keep. We propose Subsequence-Association Filtered, breadth-aware query expansion (SAFE-QE), a training-free, retriever agnostic method that draws on the subsequence-association account of hallucination. We score each candidate expansion term by its corpus conditioned cross-context reproducibility, terms that reappear under randomised query contexts yet lack support in the pseudo-relevant set are flagged as products of dominant hallucinatory associations and down-weighted. Drawing on the characterisation of language generation as a trade-off between consistency (no hallucination) and breadth (coverage), we cast term selection as constrained coverage maximisation over the pseudo-relevant set, keeping a set that is approximately broad but consistent and stable across resampling. We also introduce the Hallucinated Expansion Term Rate, a query side faithfulness metric that counts injected expansion terms no relevant document supports. We evaluate our approach on benchmarked TREC and BEIR collections. Our SAFE-QE is statistically indistinguishable from generative and corpus-steered expansion on nDCG@10 while injecting fewer unsupported terms 4.3 per query against 27.8 for Query2doc and 57.5 for HyDE and on a strong learned sparse retriever, where every expansion method regresses. Faithfulness is therefore available at no measurable cost in ranking quality.