mlsanityData to 7 Oct 2026

Query Rewriting for Retrieval-Augmented Large Language Models

arXiv 2305.14283 ↗First posted 23 May 2023cs.CLcited by 211

On the map: Retrieval-augmented generation → Generation and context integration

Abstract (arXiv)

Large Language Models (LLMs) play powerful, black-box readers in the retrieve-then-read pipeline, making remarkable progress in knowledge-intensive tasks. This work introduces a new framework, Rewrite-Retrieve-Read instead of the previous retrieve-then-read for the retrieval-augmented LLMs from the perspective of the query rewriting. Unlike prior studies focusing on adapting either the retriever or the reader, our approach pays attention to the adaptation of the search query itself, for there is inevitably a gap between the input text and the needed knowledge in retrieval. We first prompt an LLM to generate the query, then use a web search engine to retrieve contexts. Furthermore, to better align the query to the frozen modules, we propose a trainable scheme for our pipeline. A small language model is adopted as a trainable rewriter to cater to the black-box LLM reader. The rewriter is trained using the feedback of the LLM reader by reinforcement learning. Evaluation is conducted on downstream tasks, open-domain QA and multiple-choice QA. Experiments results show consistent performance improvement, indicating that our framework is proven effective and scalable, and brings a new framework for retrieval-augmented LLM.

Key facts. Cited by 211 papers in the map (data through 7 Oct 2026). Placed in Generation and context integration, one of 15 directions in Retrieval-augmented generation. Builds on 48 of its 62 references that are in the map. First posted on arXiv 23 May 2023.

Builds on

48 of 62 references.

Closest ancestors · 5

Same direction, newest first

  1. 2023REPLUG: Retrieval-Augmented Black-Box Language Models30 Jan
  2. 2022Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP28 Dec
  3. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Models5 Aug
  4. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks22 May
  5. 2020REALM: Retrieval-Augmented Language Model Pre-Training10 Feb

Other references · 43

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2022Training language models to follow instructions with human feedbackcited by 15,712
  4. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  5. 2017Proximal Policy Optimization Algorithmscited by 14,441
  6. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  7. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  8. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  9. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  10. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  11. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  12. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
31 more
  1. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  2. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  3. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  4. 2019Fine-Tuning Language Models from Human Preferencescited by 2,124
  5. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 1,916
  6. 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?cited by 1,413
  7. 2021Improving language models by retrieving from trillions of tokenscited by 1,278
  8. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
  9. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,054
  10. 2023A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivitycited by 888
  11. 2017Reading Wikipedia to Answer Open-Domain Questionscited by 777
  12. 2023AGIEval: A Human-Centric Benchmark for Evaluating Foundation Modelscited by 701
  13. 2022Automatic Chain of Thought Prompting in Large Language Modelscited by 684
  14. 2020AmbigQA: Answering Ambiguous Open-domain Questionscited by 385
  15. 2022Large Language Models Are Reasoning Teacherscited by 318
  16. 2022Generate rather than Retrieve: Large Language Models are Strong Context Generatorscited by 296
  17. 2022Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimizationcited by 244
  18. 2022Selective Annotation Makes Language Models Better Few-Shot Learnerscited by 242
  19. 2021End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answeringcited by 133
  20. 2022TemporalWiki: A Lifelong Benchmark for Training and Evaluating Ever-Evolving Language Modelscited by 117
  21. 2019JEC-QA: A Legal-Domain Question Answering Datasetcited by 115
  22. 2022Language Models that Seek for Knowledge: Modular Search & Generation for Dialogue and Prompt Completioncited by 102
  23. 2023Guiding Large Language Models via Directional Stimulus Promptingcited by 94
  24. 2021Time Waits for No One! Analysis and Challenges of Temporal Misalignmentcited by 91
  25. 2022Multi-hop Question Answeringcited by 64
  26. 2021Temporal Adaptation of BERT and Performance on Downstream Document Classification: Insights from Social Mediacited by 51
  27. 2022TEMPERA: Test-Time Prompting via Reinforcement Learningcited by 50
  28. 2022Retrieval as Attention: End-to-end Learning of Retrieval and Reading within a Single Transformercited by 45
  29. 2022Can Retriever-Augmented Language Models Reason? The Blame Game Between the Retriever and the Language Modelcited by 32
  30. 2021You Only Need One Model for Open-domain Question Answeringcited by 17
  31. 2021Sentence-aware Contrastive Learning for Open-Domain Passage Retrievalcited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 5; 2024: 61; 2025: 77; 2026: 68.

211 papers.

Sort:

By area:

  1. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  2. 2023Large Language Models for Information Retrieval: A Surveycited by 331
  3. 2025WebThinker: Empowering Large Reasoning Models with Deep Research Capabilitycited by 320
  4. 2024A Survey on Knowledge Distillation of Large Language Modelscited by 276
  5. 2024From Persona to Personalization: A Survey on Role-Playing Language Agentscited by 206
  6. 2024A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systemscited by 170
  7. 2024RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generationcited by 144
  8. 2024Language agents achieve superhuman synthesis of scientific knowledgecited by 121
  9. 2025A Survey of Context Engineering for Large Language Modelscited by 120
  10. 2024MMSearch: Benchmarking the Potential of Large Models as Multi-modal Search Enginescited by 98
  11. 2024From Matching to Generation: A Survey on Generative Information Retrievalcited by 89
  12. 2024Searching for Best Practices in Retrieval-Augmented Generationcited by 83
38 more
  1. 2024Trustworthiness in Retrieval-Augmented Generation Systems: A Surveycited by 83
  2. 2024Speculative RAG: Enhancing Retrieval Augmented Generation through Draftingcited by 76
  3. 2025ReasonIR: Training Retrievers for Reasoning Taskscited by 76
  4. 2024Retrieval Augmented Generation (RAG) and Beyond: A Comprehensive Survey on How to Make your LLMs use External Data More Wiselycited by 65
  5. 2024Inference Scaling for Long-Context Retrieval Augmented Generationcited by 65
  6. 2024Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Modelscited by 57
  7. 2026Graph-of-Skills: Dependency-Aware Structural Retrieval for Massive Agent Skillscited by 53
  8. 2024UniBind: LLM-Augmented Unified and Balanced Representation Space to Bind Them Allcited by 49
  9. 2025From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agentscited by 49
  10. 2025A Survey of Large Language Model Agents for Question Answeringcited by 46
  11. 2024Modular RAG: Transforming RAG Systems into LEGO-like Reconfigurable Frameworkscited by 41
  12. 2024Auto-RAG: Autonomous Retrieval-Augmented Generation for Large Language Modelscited by 41
  13. 2024Retrieval Augmented Time Series Forecastingcited by 40
  14. 2025Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learningcited by 39
  15. 2025Think Then Embed: Generative Context Improves Multimodal Embeddingcited by 39
  16. 2024RAR-b: Reasoning as Retrieval Benchmarkcited by 33
  17. 2024BlendFilter: Advancing Retrieval-Augmented Large Language Models via Query Generation Blending and Knowledge Filteringcited by 29
  18. 2024Retrieval-augmented generation in multilingual settingscited by 27
  19. 2024Cofca: A Step-Wise Counterfactual Multi-hop QA benchmarkcited by 26
  20. 2024DMQR-RAG: Diverse Multi-Query Rewriting for RAGcited by 26
  21. 2024Toolshed: Scale Tool-Equipped Agents with Advanced RAG-Tool Fusion and Tool Knowledge Basescited by 23
  22. 2025GraphRAG under Firecited by 23
  23. 2024ConfusedPilot: Confused Deputy Risks in RAG-based LLMscited by 22
  24. 2024A Survey of Conversational Searchcited by 22
  25. 2025MCTS-RAG: Enhancing Retrieval-Augmented Generation with Monte Carlo Tree Searchcited by 20
  26. 2024SmartRAG: Jointly Learn RAG-Related Tasks From the Environment Feedbackcited by 19
  27. 2025Collab-RAG: Boosting Retrieval-Augmented Generation for Complex Question Answering via White-Box and Black-Box LLM Collaborationcited by 19
  28. 2025Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challengescited by 19
  29. 2023Agent4Ranking: Semantic Robust Ranking via Personalized Query Rewriting Using Multi-agent LLMcited by 18
  30. 2025PIKE-RAG: sPecIalized KnowledgE and Rationale Augmented Generationcited by 18
  31. 2025RAGO: Systematic Performance Optimization for Retrieval-Augmented Generation Servingcited by 18
  32. 2024A Survey on Large Language Models from General Purpose to Medical Applications: Datasets, Methodologies, and Evaluationscited by 16
  33. 2024METIS: Fast Quality-Aware RAG Systems with Configuration Adaptationcited by 16
  34. 2025Graph RAG-Tool Fusioncited by 15
  35. 2025Tool-to-Agent Retrieval: Bridging Tools and Agents for Scalable LLM Multi-Agent Systemscited by 15
  36. 2023Context Aware Query Rewriting for Text Rankers using LLMcited by 14
  37. 2024On the Vulnerability of Applying Retrieval-Augmented Generation within Knowledge-Intensive Application Domainscited by 14
  38. 2025RaCoT: Plug-and-Play Contrastive Example Generation Mechanism for Enhanced LLM Reasoning Reliabilitycited by 14

50 most cited of 211 All 211 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Rethinking On-policy Optimization for Query Augmentation
  2. 2024MaFeRw: Query Rewriting with Multi-Aspect Feedbacks for Retrieval-Augmented Large Language Models
  3. 2025TongSearch-QR: Reinforced Query Reasoning for Retrieval
  4. 2024Supportiveness-based Knowledge Rewriting for Retrieval-augmented Language Modeling
  5. 2024RaFe: Ranking Feedback Improves Query Rewriting for RAG
  6. 2025ReZero: Enhancing LLM search ability by trying one-more-time
  7. 2026OThink-SRR1: Search, Refine and Reasoning with Reinforced Learning for Large Language Models
  8. 2023PRCA: Fitting Black-Box Large Language Models for Retrieval Question Answering via Pluggable Reward-Driven Contextual Adapter