Query Reformulation

Follow this topic Ask about this topic

Query reformulation studies how to restate, expand, decompose, or clarify a question so search systems find useful evidence, especially in conversational search, retrieval-augmented generation, and agentic research. Approaches include language-model rewriting, multi-query generation, evidence-guided refinement, retriever-specific policies, and reinforcement learning, evaluated on benchmarks such as BEIR, conversational retrieval tasks, and multi-hop question answering. Rewriting can bridge vocabulary gaps and improve recall, but may also remove useful terms, drift from intent, or add cost; gains depend on the query, corpus, and retriever. Current work therefore explores adaptive selection, intent-preserving constraints, and feedback from retrieval or downstream answers, while the balance between broader coverage and faithful, efficient search remains open.

Latest papers

42 papers4 papers in the last four weeks, down 20% on the four weeks before. 0.0% of all new papers.

A Systematic Study of Retrieval Pipeline Design for Retrieval-Augmented Medical Question Answering
Apr 8, 2026Nusrat Sultana, Abdullah Muhammad Moosa, Kazi Afzalur Rahman +1RAG Evaluation Medical QA
Department of Mechatronics & Industrial Engineering, Chittagong University of Engineering & Technology, Chittagong, Bangladesh. · Department of Mechanical Engineering, Chittagong University of Engineering & Technology, Chittagong, Bangladesh.
BRIDGE: Multimodal-to-Text Retrieval via Reinforcement-Learned Query Alignment
Apr 8, 2026Mohamed Darwish Mounis, Mohamed Mahmoud, Shaimaa Sedek +4Multimodal IR Cross-Modal Retrieval
High institute for computer & information systems · Chungbuk National University · Assiut University +1
Multi-Faceted Self-Consistent Preference Alignment for Query Rewriting in Conversational Search
Apr 8, 2026Zhiyu Cao, Peifeng Li, Qiaoming ZhuQuery Reformulation Conversational Search
School of Computer Science and Technology, Soochow University, Suzhou, China
WikiSeeker: Rethinking the Role of Vision-Language Models in Knowledge-Based Visual Question Answering
Apr 7, 2026Yingjian Zhu, Xinming Wang, Kun Ding +3Knowledge-Based VQA Multimodal RAG
School of Artificial Intelligence, University of Chinese Academy of Sciences · State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences · School of Artificial Intelligence, University of Science and Technology Beijing
ReFormeR: Learning and Applying Explicit Query Reformulation Patterns
Apr 1, 2026Amin Bigdeli, Mert Incesu, Negar Arabzadeh +2Query Reformulation LLM Prompting
University of Waterloo, Waterloo, Ontario, Canada · University of Toronto, Toronto, Ontario, Canada · University of California, Berkeley, Berkeley, California, USA
Helix: A Dual-Helix Co-Evolutionary Multi-Agent System for Prompt Optimization and Question Reformulation
Mar 20, 2026Kewen Zhu, Liping Yi, Zhiming Zhao +2Automatic Prompt Optimization Query Reformulation
College of Intelligence and Computing, Tianjin University, Tianjin, China
Hypothesis-Conditioned Query Rewriting for Decision-Useful Retrieval
Mar 19, 2026Hangeol Chang, Changsun Lee, Seungjoon Rho +2Retrieval-Augmented Generation Query Reformulation
Graduate School of AI, KAIST, Republic of Korea · School of Electrical Engineering, KAIST, Republic of Korea · Department of Industrial Engineering, Yonsei University, Republic of Korea
AILS-NTUA at SemEval-2026 Task 8: Evaluating Multi-Turn RAG Conversations
Mar 11, 2026Dimosthenis Athanasiou, Maria Lymperaiou, Giorgos Filandrianos +2Retrieval-Augmented Generation RAG Evaluation
National Technical University of Athens
Not All Queries Need Rewriting: When Prompt-Only LLM Refinement Helps and Hurts Dense Retrieval
Mar 2, 2026Varun KotteQuery Reformulation Dense Retrieval
Adobe
Query Disambiguation via Answer-Free Context: Doubling Performance on Humanity's Last Exam
Feb 27, 2026Michael Majurski, Cynthia MatuszekQuery Reformulation LLM Grounding
National Institute of Standards and Technology · University of Maryland Baltimore County
Revisiting Text Ranking in Deep Research
Feb 25, 2026Chuan Meng, Litu Ou, Sean MacAvaney +1Deep Research Agents Learning to Rank
The University of Edinburgh Edinburgh, United Kingdom · University of Glasgow Glasgow, United Kingdom
No One Size Fits All: QueryBandits for Hallucination Mitigation
Feb 23, 2026Nicole Cho, William Watson, Alec Koppel +2LLM Hallucination Mitigation Query Reformulation
JPMorgan AI Research, New York, NY, USA

Apr 8, 2026J/K move · Enter open · S save

A Systematic Study of Retrieval Pipeline Design for Retrieval-Augmented Medical Question Answering

Nusrat Sultana, Abdullah Muhammad Moosa, Kazi Afzalur Rahman, Sajal Chandra Banik

Department of Mechatronics & Industrial Engineering, Chittagong University of Engineering & Technology, Chittagong, Bangladesh. · Department of Mechanical Engineering, Chittagong University of Engineering & Technology, Chittagong, Bangladesh.

RAG Evaluation Medical QA Biomedical QA Dense Retrieval Query Reformulation

Open paper AskPDF arXiv

Large language models (LLMs) have demonstrated strong capabilities in medical question answering; however, purely parametric models often suffer from knowledge gaps and limited factual grounding. Retrieval-augmented generation (RAG) addresses this limitation by integrating external knowledge retrieval into the reasoning process. Despite increasing interest in RAG-based medical systems, the impact of individual retrieval components on performance remains insufficiently understood. This study presents a systematic evaluation of retrieval-augmented medical question answering using the MedQA USMLE benchmark and a structured textbook-based knowledge corpus. We analyze the interaction between language models, embedding models, retrieval strategies, query reformulation, and cross-encoder reranking within a unified experimental framework comprising forty configurations. Results show that retrieval augmentation significantly improves zero-shot medical question answering performance. The best-performing configuration was dense retrieval with query reformulation and reranking achieved 60.49% accuracy. Domain-specialized language models were also found to better utilize retrieved medical evidence than general-purpose models. The analysis further reveals a clear tradeoff between retrieval effectiveness and computational cost, with simpler dense retrieval configurations providing strong performance while maintaining higher throughput. All experiments were conducted on a single consumer-grade GPU, demonstrating that systematic evaluation of retrieval-augmented medical QA systems can be performed under modest computational resources.