mlsanityData to 7 Oct 2026

From Local to Global: A Graph RAG Approach to Query-Focused Summarization

arXiv 2404.16130 ↗First posted 24 Apr 2024cs.CL cs.AI cs.IRcited by 1,411

On the map: Retrieval-augmented generation → Knowledge-graph and structured-knowledge RAG

Abstract (arXiv)

The use of retrieval-augmented generation (RAG) to retrieve relevant information from an external knowledge source enables large language models (LLMs) to answer questions over private and/or previously unseen document collections. However, RAG fails on global questions directed at an entire text corpus, such as "What are the main themes in the dataset?", since this is inherently a query-focused summarization (QFS) task, rather than an explicit retrieval task. Prior QFS methods, meanwhile, do not scale to the quantities of text indexed by typical RAG systems. To combine the strengths of these contrasting methods, we propose GraphRAG, a graph-based approach to question answering over private text corpora that scales with both the generality of user questions and the quantity of source text. Our approach uses an LLM to build a graph index in two stages: first, to derive an entity knowledge graph from the source documents, then to pregenerate community summaries for all groups of closely related entities. Given a question, each community summary is used to generate a partial response, before all partial responses are again summarized in a final response to the user. For a class of global sensemaking questions over datasets in the 1 million token range, we show that GraphRAG leads to substantial improvements over a conventional RAG baseline for both the comprehensiveness and diversity of generated answers.

Key facts. Cited by 1,411 papers in the map (data through 7 Oct 2026). Placed in Knowledge-graph and structured-knowledge RAG, one of 15 directions in Retrieval-augmented generation. Builds on 40 of its 57 references that are in the map. First posted on arXiv 24 Apr 2024.

Builds on

40 of 57 references.

Closest ancestors · 5

Same direction, newest first

  1. 2024Causal Graph Discovery with Retrieval-Augmented Generation based Large Language Models23 Feb
  2. 2024G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering12 Feb
  3. 2024RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval31 Jan
  4. 2023FABULA: Intelligence Report Generation Using Retrieval-Augmented Narrative Construction20 Oct
  5. 2023Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy24 May

Other references · 35

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2023GPT-4 Technical Reportcited by 18,132
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  4. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  5. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  6. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  7. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  8. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  9. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 911
  10. 2023SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Modelscited by 787
  11. 2023In-Context Retrieval-Augmented Language Modelscited by 694
  12. 2023Is ChatGPT a Good NLG Evaluator? A Preliminary Studycited by 420
23 more
  1. 2023Ragas: Automated Evaluation of Retrieval Augmented Generationcited by 408
  2. 2018From Louvain to Leiden: guaranteeing well-connected communitiescited by 379
  3. 2022Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLPcited by 316
  4. 2024MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queriescited by 253
  5. 2020Generation-Augmented Retrieval for Open-domain Question Answeringcited by 186
  6. 2023Knowledge Graph Prompting for Multi-Document Question Answeringcited by 150
  7. 2019Hierarchical Transformers for Multi-Document Summarizationcited by 132
  8. 2023The Impact of Large Language Models on Scientific Discovery: a Preliminary Study using GPT-4cited by 112
  9. 2023Lift Yourself Up: Retrieval-augmented Text Generation with Self Memorycited by 103
  10. 2023Graph-ToolFormer: To Empower LLMs with Graph Reasoning Ability via Prompt Augmented by ChatGPTcited by 78
  11. 2021A Survey of Community Detection Approaches: From Statistical Modeling to Deep Learningcited by 55
  12. 2023Knowledge Graph-Augmented Language Models for Knowledge-Grounded Dialogue Generationcited by 54
  13. 2023Integrating Large Language Model for Improved Causal Discoverycited by 54
  14. 2023Enhancing Knowledge Graph Construction Using Large Language Modelscited by 44
  15. 2023Exploring Large Language Models for Knowledge Graph Completioncited by 43
  16. 2023Tree of Clarifications: Answering Ambiguous Questions with Retrieval-Augmented Large Language Modelscited by 42
  17. 2018Query Focused Abstractive Summarization: Incorporating Query Relevance, Multi-Document Coverage, and Summary Length Constraints into seq2seq Modelscited by 39
  18. 2024In Search of Needles in a 11M Haystack: Recurrent Memory Finds What LLMs Misscited by 36
  19. 2023Retrieval-Generation Synergy Augmented Large Language Modelscited by 26
  20. 2021Domain Adaptation with Pre-trained Transformers for Query Focused Abstractive Text Summarizationcited by 21
  21. 2024FeB4RAG: Evaluating Federated Search in the Context of Retrieval Augmented Generationcited by 19
  22. 2021Text Summarization with Latent Queriescited by 8
  23. 2019Talking datasets: Understanding data sensemaking behaviourscited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 141; 2025: 516; 2026: 754.

1,411 papers.

Sort:

By area:

  1. 2025A-MEM: Agentic Memory for LLM Agentscited by 1,000
  2. 2025Search-o1: Agentic Search-Enhanced Large Reasoning Modelscited by 423
  3. 2024Graph Retrieval-Augmented Generation: A Surveycited by 320
  4. 2024LightRAG: Simple and Fast Retrieval-Augmented Generationcited by 310
  5. 2025Memory in the Age of AI Agentscited by 285
  6. 2024HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Modelscited by 273
  7. 2024MinerU: An Open-Source Solution for Precise Document Content Extractioncited by 255
  8. 2025Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactionscited by 236
  9. 2025Large Language Model Agent: A Survey on Methodology, Applications and Challengescited by 194
  10. 2024Retrieval-Augmented Generation with Graphs (GraphRAG)cited by 170
  11. 2025LightMem: Lightweight and Efficient Memory-Augmented Generationcited by 163
  12. 2026SimpleMem: Efficient Lifelong Memory for LLM Agentscited by 140
38 more
  1. 2025BrowseComp-ZH: Benchmarking Web Browsing Ability of Large Language Models in Chinesecited by 139
  2. 2025MemOS: A Memory OS for AI Systemcited by 129
  3. 2024GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoningcited by 128
  4. 2025A Survey of Context Engineering for Large Language Modelscited by 120
  5. 2024MemoRAG: Boosting Long Context Processing with Global Memory-Enhanced Retrieval Augmentationcited by 118
  6. 2025TurboQuant: Online Vector Quantization with Near-optimal Distortion Ratecited by 116
  7. 2025Agentic Reasoning: A Streamlined Framework for Enhancing LLM Reasoning with Agentic Toolscited by 106
  8. 2024AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agentscited by 100
  9. 2024HybridRAG: Integrating Knowledge Graphs and Vector Retrieval Augmented Generation for Efficient Information Extractioncited by 92
  10. 2025Measuring Sycophancy of Language Models in Multi-turn Dialoguescited by 91
  11. 2024Medical Graph RAG: Towards Safe Medical Large Language Model via Graph Retrieval-Augmented Generationcited by 89
  12. 2024From LLMs to LLM-based Agents for Software Engineering: A Survey of Current, Challenges and Futurecited by 85
  13. 2024VerilogCoder: Autonomous Verilog Coding Agents with Graph-based Planning and Abstract Syntax Tree (AST)-based Waveform Tracing Toolcited by 85
  14. 2025A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Modelscited by 85
  15. 2025MedRAG: Enhancing Retrieval-augmented Generation with Knowledge Graph-Elicited Reasoning for Healthcare Copilotcited by 83
  16. 2025StepSearch: Igniting LLMs Search Ability via Step-Wise Proximal Policy Optimizationcited by 82
  17. 2024DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perceptioncited by 80
  18. 2024Simple Is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generationcited by 78
  19. 2024GRAG: Graph Retrieval-Augmented Generationcited by 77
  20. 2024From Isolated Conversations to Hierarchical Schemas: Dynamic Tree Memory Representation for LLMscited by 77
  21. 2025VideoRAG: Retrieval-Augmented Generation with Extreme Long-Context Videoscited by 76
  22. 2025From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discoverycited by 74
  23. 2026MemoryArena: Benchmarking Agent Memory in Interdependent Multi-Session Agentic Taskscited by 72
  24. 2024StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurizationcited by 70
  25. 2025MemOS: An Operating System for Memory-Augmented Generation (MAG) in Large Language Modelscited by 68
  26. 2026Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineeringcited by 68
  27. 2024KAG: Boosting LLMs in Professional Domains via Knowledge Augmented Generationcited by 67
  28. 2024Retrieval Augmented Generation (RAG) and Beyond: A Comprehensive Survey on How to Make your LLMs use External Data More Wiselycited by 65
  29. 2024Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generationcited by 63
  30. 2024CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph Databasescited by 62
  31. 2025PathRAG: Pruning Graph-based Retrieval Augmented Generation with Relational Pathscited by 60
  32. 2024When Search Engine Services meet Large Language Models: Visions and Challengescited by 59
  33. 2025Knowledge Graph-Guided Retrieval Augmented Generationcited by 57
  34. 2025Collaborative Memory: Multi-User Memory Sharing in LLM Agents with Dynamic Access Controlcited by 56
  35. 2026Graph-of-Skills: Dependency-Aware Structural Retrieval for Massive Agent Skillscited by 53
  36. 2025RAG vs. GraphRAG: A Systematic Evaluation and Key Insightscited by 51
  37. 2025HaluMem: Evaluating Hallucinations in Memory Systems of Agentscited by 51
  38. 2025Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learningcited by 50

50 most cited of 1,411 All 1,411 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025DSRAG: A Domain-Specific Retrieval Framework Based on Document-derived Multimodal Knowledge Graph
  2. 2025KERAG: Knowledge-Enhanced Retrieval-Augmented Generation for Advanced Question Answering
  3. 2025Clue-RAG: Towards Accurate and Cost-Efficient Graph-based RAG via Multi-Partite Graph and Query-Driven Iterative Retrieval
  4. 2026UltRAG: a Universal Simple Scalable Recipe for Knowledge Graph RAG
  5. 2025Millions of GeAR-s: Extending GraphRAG to Millions of Documents
  6. 2025mmRAG: A Modular Benchmark for Retrieval-Augmented Generation over Text, Tables, and Knowledge Graphs
  7. 2026MKG-RAG-Bench: Benchmarking Retrieval in Multimodal Knowledge Graph-Augmented Generation
  8. 2025Fusing Knowledge and Language: A Comparative Study of Knowledge Graph-Based Question Answering with LLMs