mlsanityData to 7 Oct 2026

Align Documents to Questions: Question-Oriented Document Rewriting for Retrieval-Augmented Generation

arXiv 2604.17325 ↗First posted 19 Apr 2026cs.CLcited by 0

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

Abstract (arXiv)

Retrieval-Augmented Generation (RAG) enhances the factuality of Large Language Models (LLMs) by incorporating retrieved documents and/or generated context. However, LLMs often exhibit a stylistic bias when presented with mixed contexts, favoring fluent but hallucinated generated content over factually grounded yet disorganized retrieved evidence. This phenomenon reveals that the utility of retrieved information is bottlenecked by its presentation. To bridge this gap, we propose QREAM, a style-controlled rewriter that aligns retrieved documents with a question-oriented style while preserving facts, better for LLM readers to utilize. Our framework consists of two stages: (1) QREAM-ICL, which uses stylistic seeds to guide iterative rewriting exploration; and (2) QREAM-FT, a lightweight student model distilled from denoised ICL outputs. QREAM-FT employs dual-criteria rejection sampling, filtering based on answer correctness and factual consistency to ensure high-quality supervision. QREAM seamlessly integrates into existing RAG pipelines as a plug-and-play module. Experiments demonstrate that QREAM consistently enhances advanced RAG pipelines, yielding up to 8% relative improvement with negligible latency overhead, effectively balancing question relevance with factual grounding.

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 25 of its 36 references that are in the map. First posted on arXiv 19 Apr 2026.

Builds on

25 of 36 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection17 Oct

Other references · 24

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2024The Llama 3 Herd of Modelscited by 14,192
  3. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  4. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  5. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  6. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  7. 2019Language Models as Knowledge Bases?cited by 1,922
  8. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,259
  9. 2023FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generationcited by 1,259
  10. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
  11. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,103
  12. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 820
12 more
  1. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 786
  2. 2023LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compressioncited by 443
  3. 2023Making Retrieval-Augmented Language Models Robust to Irrelevant Contextcited by 364
  4. 2022Generate rather than Retrieve: Large Language Models are Strong Context Generatorscited by 296
  5. 2021Generated Knowledge Prompting for Commonsense Reasoningcited by 213
  6. 2023Head-to-Tail: How Knowledgeable are Large Language Models (LLMs)? A.K.A. Will LLMs Replace Knowledge Graphs?cited by 167
  7. 2022Improving Passage Retrieval with Zero-Shot Question Generationcited by 164
  8. 2023The Troubling Emergence of Hallucination in Large Language Models -- An Extensive Definition, Quantification, and Prescriptive Remediationscited by 130
  9. 2024CompAct: Compressing Retrieved Documents Actively for Question Answeringcited by 64
  10. 2024Blinded by Generated Contexts: How Language Models Merge Generated and Retrieved Contexts When Knowledge Conflicts?cited by 47
  11. 2023Merging Generated and Retrieved Knowledge for Open-Domain QAcited by 36
  12. 2024Perception of Knowledge Boundary for Large Language Models through Semi-open-ended Question Answeringcited by 20

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation
  2. 2025Read the Docs Before Rewriting: Equip Rewriter with Domain Knowledge via Continual Pre-training
  3. 2025Question Decomposition for Retrieval-Augmented Generation
  4. 2025Transforming Questions and Documents for Semantically Aligned Retrieval-Augmented Generation
  5. 2024Refiner: Restructure Retrieval Content Efficiently to Advance Question-Answering Capabilities
  6. 2025Investigating the Robustness of Retrieval-Augmented Generation at the Query Level
  7. 2024PA-RAG: RAG Alignment via Multi-Perspective Preference Optimization
  8. 2025Domain-Specific Data Generation Framework for RAG Adaptation