mlsanityData to 7 Oct 2026

Hypothesis-Conditioned Query Rewriting for Decision-Useful Retrieval

arXiv 2603.19008 ↗First posted 19 Mar 2026cs.CL cs.AI cs.LGcited by 0

On the map: Retrieval-augmented generation → RAG robustness and adaptive retrieval

Abstract (arXiv)

Retrieval-Augmented Generation (RAG) improves Large Language Models (LLMs) by grounding generation in external, non-parametric knowledge. However, when a task requires choosing among competing options, simply grounding generation in broadly relevant context is often insufficient to drive the final decision. Existing RAG methods typically rely on a single initial query, which often favors topical relevance over decision-relevant evidence, and therefore retrieves background information that can fail to discriminate among answer options. To address this issue, here we propose Hypothesis-Conditioned Query Rewriting (HCQR), a training-free pre-retrieval framework that reorients RAG from topic-oriented retrieval to evidence-oriented retrieval. HCQR first derives a lightweight working hypothesis from the input question and candidate options, and then rewrites retrieval into three targeted queries that seek evidence to: (1) support the hypothesis, (2) distinguish it from competing alternatives, and (3) verify salient clues in the question. This approach enables context retrieval that is more directly aligned with answer selection, allowing the generator to confirm or overturn the initial hypothesis based on the retrieved evidence. Experiments on MedQA and MMLU-Med show that HCQR consistently outperforms single-query RAG and re-rank/filter baselines, improving average accuracy over Simple RAG by 5.9 and 3.6 points, respectively. Code is available at https://anonymous.4open.science/r/HCQR-1C2E.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 16 of its 20 references that are in the map. First posted on arXiv 19 Mar 2026.

Builds on

16 of 20 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025The Distracting Effect: Understanding Irrelevant Passages in RAG11 May
  2. 2024Sufficient Context: A New Lens on Retrieval Augmented Generation Systems9 Nov
  3. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection17 Oct

Other references · 13

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  3. 2020What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Examscited by 1,324
  4. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 911
  5. 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 508
  6. 2023Making Retrieval-Augmented Language Models Robust to Irrelevant Contextcited by 364
  7. 2024Benchmarking Retrieval-Augmented Generation for Medicinecited by 326
  8. 2024RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMscited by 200
  9. 2023MedCPT: Contrastive Pre-trained Transformers with Large-scale PubMed Search Logs for Zero-shot Biomedical Information Retrievalcited by 182
  10. 2025Context Length Alone Hurts LLM Performance Despite Perfect Retrievalcited by 118
  11. 2024Improving Retrieval-Augmented Generation in Medicine with Iterative Follow-up Questionscited by 54
  12. 2024MAIN-RAG: Multi-Agent Filtering Retrieval-Augmented Generationcited by 43
1 more
  1. 2025Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challengescited by 19

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Enhancing Retrieval-Augmented Generation with Two-Stage Retrieval: FlashRank Reranking and Query Expansion
  2. 2026Rethinking the Reranker: Boundary-Aware Evidence Selection for Robust Retrieval-Augmented Generation
  3. 2025Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontiers
  4. 2024RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation
  5. 2026CQC-RAG: Robust Retrieval-Augmented Generation via Cross-Query Consistency
  6. 2026Decide Then Retrieve: A Training-Free Framework with Uncertainty-Guided Triggering and Dual-Path Retrieval
  7. 2025Investigating the Robustness of Retrieval-Augmented Generation at the Query Level
  8. 2026Stateful Evidence-Driven Retrieval-Augmented Generation with Iterative Reasoning