mlsanityData to 14 Oct 2026

A Survey of Query Optimization in Large Language Models

arXiv 2412.17558 ↗First posted 23 Dec 2024cs.CLcited by 1

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

Abstract (arXiv)

Query Optimization (QO) has become essential for enhancing Large Language Model (LLM) effectiveness, particularly in Retrieval-Augmented Generation (RAG) systems where query quality directly determines retrieval and response performance. This survey provides a systematic and comprehensive analysis of query optimization techniques with three principal contributions. textitFirst, we introduce the Query Optimization Lifecycle (QOL) Framework, a five-phase pipeline covering Intent Recognition, Query Transformation, Retrieval Execution, Evidence Integration, and Response Synthesis, providing a unified lens for understanding the optimization process. textitSecond, we propose a Query Complexity Taxonomy that classifies queries along two dimensions, namely evidence type (explicit vs. implicit) and evidence quantity (single vs. multiple), establishing principled mappings between query characteristics and optimization strategies. textitThird, we conduct an in-depth analysis of four atomic operations, namely Query Expansion, Query Decomposition, Query Disambiguation, and Query Abstraction, synthesizing a broad spectrum of representative methods from premier venues. We further examine evaluation methodologies, identify critical gaps in existing benchmarks, and discuss open challenges including process reward models, efficiency optimization, and multi-modal query handling. This survey offers both a structured foundation for research and actionable guidance for practitioners.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 112 of its 130 references that are in the map. First posted on arXiv 23 Dec 2024.

Builds on

112 of 130 references.

Closest ancestors · 15

Same direction, newest first

  1. 2024Query Optimization for Parametric Knowledge Refinement in Retrieval-Augmented Large Language Models12 Nov
  2. 2024Do RAG Systems Cover What Matters? Evaluating and Optimizing Responses with Sub-Question Coverage20 Oct
  3. 2024ConTReGen: Context-driven Tree-structured Retrieval for Open-domain Long-form Text Generation20 Oct
  4. 2024RuleRAG: Rule-Guided Retrieval-Augmented Generation with Language Models for Question Answering15 Oct
  5. 2024Retrieving, Rethinking and Revising: The Chain-of-Verification Can Improve Retrieval Augmented Generation8 Oct
  6. 2024RAG-QA Arena: Evaluating Domain Robustness for Long-form Retrieval Augmented Question Answering19 Jul
  7. 2024RichRAG: Crafting Rich Responses for Multi-faceted Queries in Retrieval-Augmented Generation18 Jun
  8. 2024DR-RAG: Applying Dynamic Document Relevance to Retrieval-Augmented Generation for Question-Answering11 Jun
  9. 2024RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation31 Mar
  10. 2024Evidence-Driven Retrieval Augmented Response Generation for Online Misinformation22 Mar
  11. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity21 Mar
  12. 2024RA-ISF: Learning to Answer and Understand from Retrieval Augmentation via Iterative Self-Feedback11 Mar
3 more
  1. 2024BlendFilter: Advancing Retrieval-Augmented Large Language Models via Query Generation Blending and Knowledge Filtering16 Feb
  2. 2023Tree of Clarifications: Answering Ambiguous Questions with Retrieval-Augmented Large Language Models23 Oct
  3. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection17 Oct

Other references · 97

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  4. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  5. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  6. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
  7. 2023A Survey of Large Language Modelscited by 2,576
  8. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  9. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
  10. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,407
  11. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,282
  12. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,075
38 more
  1. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 923
  2. 2021MuSiQue: Multihop Questions via Single-hop Question Compositioncited by 916
  3. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 792
  4. 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 698
  5. 2023Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Modelscited by 560
  6. 2022Decomposed Prompting: A Modular Approach for Solving Complex Taskscited by 558
  7. 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 517
  8. 2023Active Retrieval Augmented Generationcited by 516
  9. 2022Large Language Models Struggle to Learn Long-Tail Knowledgecited by 458
  10. 2024A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Modelscited by 452
  11. 2023Ragas: Automated Evaluation of Retrieval Augmented Generationcited by 418
  12. 2023Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergycited by 346
  13. 2023Large Language Models for Information Retrieval: A Surveycited by 331
  14. 2024Graph Retrieval-Augmented Generation: A Surveycited by 324
  15. 2022Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLPcited by 318
  16. 2024LightRAG: Simple and Fast Retrieval-Augmented Generationcited by 315
  17. 2022Generate rather than Retrieve: Large Language Models are Strong Context Generatorscited by 298
  18. 2024Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoningcited by 279
  19. 2024A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Modelscited by 269
  20. 2023ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systemscited by 265
  21. 2022Promptagator: Few-shot Dense Retrieval From 8 Examplescited by 235
  22. 2023Query Rewriting for Retrieval-Augmented Large Language Modelscited by 213
  23. 2024RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMscited by 202
  24. 2024Corrective Retrieval Augmented Generationcited by 197
  25. 2023Take a Step Back: Evoking Reasoning via Abstraction in Large Language Modelscited by 159
  26. 2023Query2doc: Query Expansion with Large Language Modelscited by 149
  27. 2020Open-Domain Question Answering Goes Conversational via Question Rewritingcited by 148
  28. 2024Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solverscited by 138
  29. 2023Deductive Verification of Chain-of-Thought Reasoningcited by 124
  30. 2023Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sourcescited by 122
  31. 2023Let's reward step by step: Step-Level reward model as the Navigators for Reasoningcited by 102
  32. 2021TopiOCQA: Open-domain Conversational Question Answering with Topic Switchingcited by 96
  33. 2022Successive Prompting for Decomposing Complex Questionscited by 94
  34. 2023Improving Language Models via Plug-and-Play Retrieval Feedbackcited by 87
  35. 2024A Survey on Retrieval-Augmented Text Generation for Large Language Modelscited by 77
  36. 2024Speculative RAG: Enhancing Retrieval Augmented Generation through Draftingcited by 77
  37. 2023Large Language Models Know Your Contextual Search Intent: A Prompting Framework for Conversational Searchcited by 75
  38. 2024RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generationcited by 75

50 most cited of 97 All 97 (JSON)

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Cite Pretrain: Retrieval-Free Knowledge Attribution for Large Language Modelscited by 2

Similar, not cited

Close in wording, no citation either way

  1. 2025Investigating the Robustness of Retrieval-Augmented Generation at the Query Level
  2. 2026DF-RAG: Query-Aware Diversity for Retrieval-Augmented Generation
  3. 2025ExpandR: Teaching Dense Retrievers Beyond Queries with LLM Guidance
  4. 2024Toward Optimal Search and Retrieval for RAG
  5. 2024Towards Optimizing a Retrieval Augmented Generation using Large Language Model on Academic Data
  6. 2026Decide Then Retrieve: A Training-Free Framework with Uncertainty-Guided Triggering and Dual-Path Retrieval
  7. 2026Mapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoning
  8. 2025SEFRQO: A Self-Evolving Fine-Tuned RAG-Based Query Optimizer