mlsanityData to 7 Oct 2026

Searching for Best Practices in Retrieval-Augmented Generation

arXiv 2407.01219 ↗First posted 1 Jul 2024cs.CLcited by 83

On the map: Retrieval-augmented generation → Multimodal RAG

Abstract (arXiv)

Retrieval-augmented generation (RAG) techniques have proven to be effective in integrating up-to-date information, mitigating hallucinations, and enhancing response quality, particularly in specialized domains. While many RAG approaches have been proposed to enhance large language models through query-dependent retrievals, these approaches still suffer from their complex implementation and prolonged response times. Typically, a RAG workflow involves multiple processing steps, each of which can be executed in various ways. Here, we investigate existing RAG approaches and their potential combinations to identify optimal RAG practices. Through extensive experiments, we suggest several strategies for deploying RAG that balance both performance and efficiency. Moreover, we demonstrate that multimodal retrieval techniques can significantly enhance question-answering capabilities about visual inputs and accelerate the generation of multimodal content using a "retrieval as generation" strategy.

Key facts. Cited by 83 papers in the map (data through 7 Oct 2026). Placed in Multimodal RAG, one of 15 directions in Retrieval-augmented generation. Builds on 66 of its 78 references that are in the map. First posted on arXiv 1 Jul 2024.

Builds on

66 of 78 references.

References · 66

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  4. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  5. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  6. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  7. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  8. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,710
  9. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
  10. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  11. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  12. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,919
38 more
  1. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  2. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  3. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  4. 2018Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answeringcited by 2,114
  5. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  6. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,591
  7. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,362
  8. 2019PubMedQA: A Dataset for Biomedical Research Question Answeringcited by 1,271
  9. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,259
  10. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,225
  11. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,216
  12. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
  13. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,054
  14. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 940
  15. 2021MuSiQue: Multihop Questions via Single-hop Question Compositioncited by 893
  16. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 786
  17. 2023Towards General Text Embeddings with Multi-stage Contrastive Learningcited by 705
  18. 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 695
  19. 2017The NarrativeQA Reading Comprehension Challengecited by 590
  20. 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 508
  21. 2023RRHF: Rank Responses to Align Language Models with Human Feedback without tearscited by 454
  22. 2023LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compressioncited by 443
  23. 2023Ragas: Automated Evaluation of Retrieval Augmented Generationcited by 408
  24. 2023SLiC-HF: Sequence Likelihood Calibration with Human Feedbackcited by 395
  25. 2020Document Ranking with a Pretrained Sequence-to-Sequence Modelcited by 373
  26. 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 352
  27. 2020Overview of the TREC 2019 deep learning trackcited by 282
  28. 2023LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Modelscited by 279
  29. 2023Fine-Tuning LLaMA for Multi-Stage Text Retrievalcited by 271
  30. 2023Generating Images with Multimodal Language Modelscited by 259
  31. 2024RAFT: Adapting Language Model to Domain Specific RAGcited by 258
  32. 2023RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentationcited by 253
  33. 2022ASQA: Factoid Questions Meet Long-Form Answerscited by 231
  34. 2023Query Rewriting for Retrieval-Augmented Large Language Modelscited by 211
  35. 2019Multi-Stage Document Ranking with BERTcited by 200
  36. 2023RA-DIT: Retrieval-Augmented Dual Instruction Tuningcited by 194
  37. 2021Overview of the TREC 2020 deep learning trackcited by 193
  38. 2022A Survey on Retrieval-Augmented Text Generationcited by 157

50 most cited of 66 All 66 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 13; 2025: 47; 2026: 23.

83 papers.

Sort:

By area:

  1. 2025A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Modelscited by 85
  2. 2025KVLink: Accelerating Large Language Models via Efficient KV Cache Reusecited by 60
  3. 2025When to use Graphs in RAG: A Comprehensive Analysis for Graph Retrieval-Augmented Generationcited by 46
  4. 2025Information Gain-based Policy Optimization: A Simple and Effective Approach for Multi-Turn Search Agentscited by 43
  5. 2024Modular RAG: Transforming RAG Systems into LEGO-like Reconfigurable Frameworkscited by 41
  6. 2025A Systematic Review of Key Retrieval-Augmented Generation (RAG) Systems: Progress, Gaps, and Future Directionscited by 30
  7. 2025Synergizing RAG and Reasoning: A Systematic Reviewcited by 27
  8. 2024DMQR-RAG: Diverse Multi-Query Rewriting for RAGcited by 26
  9. 2025Atom-Searcher: Enhancing Agentic Deep Research via Fine-Grained Atomic Thought Rewardcited by 25
  10. 2024SiReRAG: Indexing Similar and Related Information for Multihop Reasoningcited by 23
  11. 2025Enhancing Retrieval-Augmented Generation: A Study of Best Practicescited by 22
  12. 2024Signs as Tokens: A Retrieval-Enhanced Multilingual Sign Language Generatorcited by 20
38 more
  1. 2024MINTQA: A Multi-Hop Question Answering Benchmark for Evaluating LLMs on New and Tail Knowledgecited by 20
  2. 2025Efficient Context Selection for Long-Context QA: No Tuning, No Iteration, Just Adaptive-kcited by 19
  3. 2024METIS: Fast Quality-Aware RAG Systems with Configuration Adaptationcited by 16
  4. 2025Resolving Conflicting Evidence in Automated Fact-Checking: A Study on Retrieval-Augmented LLMscited by 16
  5. 2025CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Executioncited by 14
  6. 2025MAGNET: A Multi-agent Framework for Finding Audio-Visual Needles by Reasoning over Multi-Video Haystackscited by 11
  7. 2025SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compressioncited by 9
  8. 2025RAGRouter: Learning to Route Queries to Multiple Retrieval-Augmented Language Modelscited by 8
  9. 2024Retrieval-Augmented Test Generation: How Far Are We?cited by 7
  10. 2024Understanding the Fundamental Design Decisions of Retrieval-Augmented Generation Systemscited by 7
  11. 2025Integrating Chain-of-Thought and Retrieval Augmented Generation Enhances Rare Disease Diagnosis from Clinical Notescited by 7
  12. 2025AURA: A Fine-Grained Benchmark and Decomposed Metric for Audio-Visual Reasoningcited by 7
  13. 2025NeuroGenPoisoning: Neuron-Guided Attacks on Retrieval-Augmented Generation of LLM via Genetic Optimization of External Knowledgecited by 7
  14. 2024Multi-Document Financial Question Answering using LLMscited by 6
  15. 2025RAGVA: Engineering Retrieval Augmented Generation-based Virtual Assistants in Practicecited by 6
  16. 2024RAG Foundry: A Framework for Enhancing LLMs for Retrieval Augmented Generationcited by 5
  17. 2025Hybrid Retrieval for Hallucination Mitigation in Large Language Models: A Comparative Analysiscited by 5
  18. 2025LogiDebrief: A Signal-Temporal Logic based Automated Debriefing Approach with Large Language Models Integrationcited by 5
  19. 2025Task Memory Engine: Spatial Memory for Robust Multi-Step LLM Agentscited by 5
  20. 2025RAGOps: Operating and Managing Retrieval-Augmented Generation Pipelinescited by 5
  21. 2026SAGEO Arena: A Realistic Environment for Evaluating Search-Augmented Generative Engine Optimizationcited by 5
  22. 2025Qilin: A Multimodal Information Retrieval Dataset with APP-level User Sessionscited by 4
  23. 2025Sign Language Translation using Frame and Event Stream: Benchmark Dataset and Algorithmscited by 4
  24. 2025OpenRAG: Optimizing RAG End-to-End via In-Context Retrieval Learningcited by 4
  25. 2025GenerationPrograms: Fine-grained Attribution with Executable Programscited by 4
  26. 2025Metadata-Driven Retrieval-Augmented Generation for Financial Question Answeringcited by 4
  27. 2025From Recall to Reasoning: Automated Question Generation for Deeper Math Learning through Large Language Modelscited by 3
  28. 2025MSQA: Benchmarking LLMs on Graduate-Level Materials Science Reasoning and Knowledgecited by 3
  29. 2025Engineering RAG Systems for Real-World Applications: Design, Development, and Evaluationcited by 3
  30. 2026CrisiSense-RAG: Crisis Sensing Multimodal Retrieval-Augmented Generation for Rapid Disaster Impact Assessmentcited by 3
  31. 2026Towards Secure Retrieval-Augmented Generation: A Comprehensive Review of Threats, Defenses and Benchmarkscited by 3
  32. 2024G-RAG: Knowledge Expansion in Material Sciencecited by 2
  33. 2025Advancing Retrieval-Augmented Generation for Persian: Development of Language Models, Comprehensive Benchmarks, and Best Practices for Optimizationcited by 2
  34. 2025Towards an automated workflow in materials science for combining multi-modal simulative and experimental information using data mining and large language modelscited by 2
  35. 2025Balancing Content Size in RAG-Text2SQL Systemcited by 2
  36. 2025An Agile Method for Implementing Retrieval Augmented Generation Tools in Industrial SMEscited by 2
  37. 2025A2Search: Ambiguity-Aware Question Answering with Reinforcement Learningcited by 2
  38. 2026Information Gain-based Rollout Policy Optimization: An Adaptive Tree-Structured Rollout Approach for Multi-Turn LLM Agentscited by 2

50 most cited of 83 All 83 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024A Comprehensive Survey of Retrieval-Augmented Generation (RAG): Evolution, Current Landscape and Future Directions
  2. 2025A Survey on Knowledge-Oriented Retrieval-Augmented Generation
  3. 2025Re-ranking the Context for Multimodal Retrieval Augmented Generation
  4. 2025RAG-Check: Evaluating Multimodal Retrieval Augmented Generation Performance
  5. 2025Ask in Any Modality: A Comprehensive Survey on Multimodal Retrieval-Augmented Generation
  6. 2025Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontiers
  7. 2024Introducing a new hyper-parameter for RAG: Context Window Utilization
  8. 2024Toward Optimal Search and Retrieval for RAG