mlsanityData to 14 Oct 2026

A Survey on Knowledge-Oriented Retrieval-Augmented Generation

arXiv 2503.10677 ↗First posted 11 Mar 2025cs.CL cs.AIcited by 36

On the map: Retrieval-augmented generation → RAG pipeline design and evaluation

Abstract (arXiv)

Retrieval-Augmented Generation (RAG) has gained significant attention in recent years for its potential to enhance natural language understanding and generation by combining large-scale retrieval systems with generative models. RAG leverages external knowledge sources, such as documents, databases, or structured data, to improve model performance and generate more accurate and contextually relevant outputs. This survey aims to provide a comprehensive overview of RAG by examining its fundamental components, including retrieval mechanisms, generation processes, and the integration between the two. We discuss the key characteristics of RAG, such as its ability to augment generative models with dynamic external knowledge, and the challenges associated with aligning retrieved information with generative objectives. We also present a taxonomy that categorizes RAG methods, ranging from basic retrieval-augmented approaches to more advanced models incorporating multimodal data and reasoning capabilities. Additionally, we review the evaluation benchmarks and datasets commonly used to assess RAG systems, along with a detailed exploration of its applications in fields such as question answering, summarization, and information retrieval. Finally, we highlight emerging research directions and opportunities for improving RAG systems, such as enhanced retrieval efficiency, model interpretability, and domain-specific adaptations. This paper concludes by outlining the prospects for RAG in addressing real-world challenges and its potential to drive further advancements in natural language processing.

Key facts. Cited by 36 papers in the map (data through 14 Oct 2026). Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation. Builds on 166 of its 273 references that are in the map. First posted on arXiv 11 Mar 2025.

Builds on

166 of 273 references.

Closest ancestors · 12

Same direction, newest first

  1. 2025Parametric Retrieval Augmented Generation27 Jan
  2. 2024HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systems5 Nov
  3. 2024Probing-RAG: Self-Probing to Guide Language Models in Selective Document Retrieval17 Oct
  4. 2024Retrieval-Augmented Generation for Natural Language Processing: A Survey18 Jul
  5. 2024PlanRAG: A Plan-then-Retrieval Augmented Generation for Generative Large Language Models as Decision Makers18 Jun
  6. 2024Evaluation of Retrieval-Augmented Generation: A Survey13 May
  7. 2024A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models10 May
  8. 2024Improving Retrieval for RAG based Question Answering Models on Financial Documents23 Mar
  9. 2024Blended RAG: Improving RAG (Retriever-Augmented Generation) Accuracy with Semantic Search and Hybrid Query-Based Retrievers22 Mar
  10. 2024Retrieval-Augmented Generation for AI-Generated Content: A Survey29 Feb
  11. 2023ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systems16 Nov
  12. 2022A Survey on Retrieval-Augmented Text Generation2 Feb

Other references · 154

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  5. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  6. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,375
  7. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,307
  8. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,148
  9. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
  10. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  11. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  12. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,474
38 more
  1. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  2. 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,790
  3. 2017Billion-scale similarity search with GPUscited by 2,497
  4. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
  5. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  6. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,745
  7. 2021ViViT: A Video Vision Transformercited by 1,620
  8. 2016Enriching Word Vectors with Subword Informationcited by 1,583
  9. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
  10. 2018Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarizationcited by 1,317
  11. 2021Improving language models by retrieving from trillions of tokenscited by 1,293
  12. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,282
  13. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,210
  14. 2020ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTcited by 1,178
  15. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,075
  16. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 923
  17. 2021MuSiQue: Multihop Questions via Single-hop Question Compositioncited by 916
  18. 2016Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphscited by 861
  19. 2020Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrievalcited by 849
  20. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 841
  21. 2019Generalization through Memorization: Nearest Neighbor Language Modelscited by 800
  22. 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 743
  23. 2022Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentationcited by 719
  24. 2023In-Context Retrieval-Augmented Language Modelscited by 702
  25. 2022MTEB: Massive Text Embedding Benchmarkcited by 640
  26. 2017The NarrativeQA Reading Comprehension Challengecited by 597
  27. 2023Enabling Large Language Models to Generate Text with Citationscited by 595
  28. 2023C-Pack: Packed Resources For General Chinese Embeddingscited by 578
  29. 2020KILT: a Benchmark for Knowledge Intensive Language Taskscited by 573
  30. 2018Wizard of Wikipedia: Knowledge-Powered Conversational agentscited by 530
  31. 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 517
  32. 2024Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Modelcited by 483
  33. 2024NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Modelscited by 472
  34. 2023LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compressioncited by 453
  35. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 451
  36. 2020How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answeringcited by 445
  37. 2017Zero-Shot Relation Extraction via Reading Comprehensioncited by 426
  38. 2023Making Retrieval-Augmented Language Models Robust to Irrelevant Contextcited by 369

50 most cited of 154 All 154 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 17; 2026: 19.

36 papers.

Sort:

By area:

  1. 2025A Survey of Context Engineering for Large Language Modelscited by 126
  2. 2025From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agentscited by 51
  3. 2025Atom-Searcher: Enhancing Agentic Deep Research via Fine-Grained Atomic Thought Rewardcited by 25
  4. 2025Retrieval Augmented Generation Evaluation in the Era of Large Language Models: A Comprehensive Surveycited by 20
  5. 2025PaperArena: An Evaluation Benchmark for Tool-Augmented Agentic Reasoning on Scientific Literaturecited by 15
  6. 2025am-ELO: A Stable Framework for Arena-based LLM Evaluationcited by 8
  7. 2025LayoutCoT: Unleashing the Deep Reasoning Potential of Large Language Models for Layout Generationcited by 7
  8. 2025BioMedSearch: A Multi-Source Biomedical Retrieval Framework Based on LLMscited by 4
  9. 2025HGMEM: Hypergraph-based Working Memory to Improve Multi-step RAG for Long-Context Complex Relational Modelingcited by 4
  10. 2025Reflexive Prompt Engineering: A Framework for Responsible Prompt Engineering and Interaction Designcited by 2
  11. 2025An Agile Method for Implementing Retrieval Augmented Generation Tools in Industrial SMEscited by 2
  12. 2025Leveraging Multi-Agent System (MAS) and Fine-Tuned Small Language Models (SLMs) for Automated Telecom Network Troubleshootingcited by 2
24 more
  1. 2026Mind2Report: Expert-Level Commercial Report Synthesis via Cognitive Deep Research Agentcited by 2
  2. 2026Financial Transaction Retrieval and Contextual Evidence for Knowledge-Grounded Reasoningcited by 2
  3. 2025Meet Your New Client: Writing Reports for AI -- Benchmarking Information Loss in Market Research Deliverablescited by 1
  4. 2025Think Less, Label Better: Multi-Stage Domain-Grounded Synthetic Data Generation for Fine-Tuning Large Language Models in Telecommunicationscited by 1
  5. 2026S3-Attention:Attention-Aligned Endogenous Retrieval for Memory-Bounded Long-Context Inferencecited by 1
  6. 2026Training Large Reasoning Models Efficiently via Progressive Thought Encodingcited by 1
  7. 2026GAM-RAG: Gain-Adaptive Memory for Evolving Retrieval in Retrieval-Augmented Generationcited by 1
  8. 2026AMATA: Adaptive Multi-Agent Trajectory Alignment for Knowledge-Intensive Question Answeringcited by 1
  9. 2026Bridging the Question-Answer Gap in Retrieval-Augmented Generation: Hypothetical Prompt Embeddingscited by 1
  10. 2025Agentic publications: redesigning scientific publishing in the age of thinking large language modelscited by 0
  11. 2025RACE-Align: Retrieval-Augmented and Chain-of-Thought Enhanced Preference Alignment for Large Language Modelscited by 0
  12. 2025Retrieval-Augmented Prompt for OOD Detectioncited by 0
  13. 2026Multi-Dimensional Knowledge Profiling with Large-Scale Literature Database and Hierarchical Retrievalcited by 0
  14. 2026Differentially Private Datastore Generation for Retrieval-Augmented Inferencecited by 0
  15. 2026Hybrid-IR: Dual-Path Hybrid Retrieval with Iterative Reasoning for Complex Medical Question Answeringcited by 0
  16. 2026GRACE-RAG: Governed Retrieval Architecture for Canonical Evidence Synthesis, Enabling Lightweight Deployment in Closed-Domain Institutional Settingscited by 0
  17. 2026When RAG Meets Query Planning: Logical Query Trees for Resolving Exploratory Reasoning Problemscited by 0
  18. 2026Healthier LLMs: Retrieval-Augmented Generation for Public Health Question Answeringcited by 0
  19. 2026G-SHARE: A Guideline-Based Structured Reasoning Framework for Human-Factor Event Diagnosiscited by 0
  20. 2026CTRAG: An In-Context Retrieval-based Framework for Automated Compliance Checking using LLMscited by 0
  21. 2026StocksTalk: A Voice-Enabled Conversational Agent for Structured Query Generation over Web Datacited by 0
  22. 2026FootprintRAG: Visual Analytics for Evidence Context Refinement in RAG-based Scientific Literature Explorationcited by 0
  23. 2026Hop-Decayed Influence: New Vulnerabilities of Structural Auxiliary Indexing in GraphRAG Pipelines with LLMcited by 0
  24. 2026Analyzing performance of Retrieval Augmented Generation models for Question Answering Taskscited by 0

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 Systematic Review of Key Retrieval-Augmented Generation (RAG) Systems: Progress, Gaps, and Future Directions
  3. 2025RAGTrace: Understanding and Refining Retrieval-Generation Dynamics in Retrieval-Augmented Generation
  4. 2025Enhancing Retrieval-Augmented Generation: A Study of Best Practices
  5. 2025Dynamic and Parametric Retrieval-Augmented Generation
  6. 2025Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontiers
  7. 2024Meta Knowledge for Retrieval Augmented Large Language Models
  8. 2024Searching for Best Practices in Retrieval-Augmented Generation