mlsanityData to 7 Oct 2026

KAG: Boosting LLMs in Professional Domains via Knowledge Augmented Generation

arXiv 2409.13731 ↗First posted 10 Sep 2024cs.CL cs.AIcited by 67

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

Abstract (arXiv)

The recently developed retrieval-augmented generation (RAG) technology has enabled the efficient construction of domain-specific applications. However, it also has limitations, including the gap between vector similarity and the relevance of knowledge reasoning, as well as insensitivity to knowledge logic, such as numerical values, temporal relations, expert rules, and others, which hinder the effectiveness of professional knowledge services. In this work, we introduce a professional domain knowledge service framework called Knowledge Augmented Generation (KAG). KAG is designed to address the aforementioned challenges with the motivation of making full use of the advantages of knowledge graph(KG) and vector retrieval, and to improve generation and reasoning performance by bidirectionally enhancing large language models (LLMs) and KGs through five key aspects: (1) LLM-friendly knowledge representation, (2) mutual-indexing between knowledge graphs and original chunks, (3) logical-form-guided hybrid reasoning engine, (4) knowledge alignment with semantic reasoning, and (5) model capability enhancement for KAG. We compared KAG with existing RAG methods in multihop question answering and found that it significantly outperforms state-of-theart methods, achieving a relative improvement of 19.6% on 2wiki and 33.5% on hotpotQA in terms of F1 score. We have successfully applied KAG to two professional knowledge Q&A tasks of Ant Group, including E-Government Q&A and E-Health Q&A, achieving significant improvement in professionalism compared to RAG methods.

Key facts. Cited by 67 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 54 of its 86 references that are in the map. First posted on arXiv 10 Sep 2024.

Builds on

54 of 86 references.

Closest ancestors · 6

Same direction, newest first

  1. 2024Graph Retrieval-Augmented Generation: A Survey15 Aug
  2. 2024Retrieve, Summarize, Plan: Advancing Multi-hop Question Answering with an Iterative Approach18 Jul
  3. 2024Learning to Plan for Retrieval-Augmented Large Language Models from Knowledge Graphs20 Jun
  4. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarization24 Apr
  5. 2024RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval31 Jan
  6. 2023Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy24 May

Other references · 48

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  4. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  5. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  6. 2019Fine-Tuning Language Models from Human Preferencescited by 2,124
  7. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,259
  8. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
  9. 2024DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Modelcited by 1,093
  10. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 911
  11. 2021MuSiQue: Multihop Questions via Single-hop Question Compositioncited by 893
  12. 2021ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interactioncited by 464
36 more
  1. 2021Large Dual Encoders Are Generalizable Retrieverscited by 454
  2. 2024A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Modelscited by 450
  3. 2023StructGPT: A General Framework for Large Language Model to Reason over Structured Datacited by 339
  4. 2023Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoningcited by 326
  5. 2023Benchmarking Large Language Models in Retrieval-Augmented Generationcited by 307
  6. 2024HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Modelscited by 273
  7. 2023Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Modelscited by 180
  8. 2020Beyond I.I.D.: Three Levels of Generalization for Question Answering on Knowledge Basescited by 169
  9. 2021Case-based Reasoning for Natural Language Queries over Knowledge Basescited by 107
  10. 2023AnglE-optimized Text Embeddingscited by 98
  11. 2024HybridRAG: Integrating Knowledge Graphs and Vector Retrieval Augmented Generation for Efficient Information Extractioncited by 92
  12. 2019ASER: A Large-scale Eventuality Knowledge Graphcited by 89
  13. 2023Dense X Retrieval: What Retrieval Granularity Should We Use?cited by 88
  14. 2022Don't Generate, Discriminate: A Proposal for Grounding Language Models to Real-World Environmentscited by 57
  15. 2023Knowledge Graph-Augmented Language Models for Knowledge-Grounded Dialogue Generationcited by 54
  16. 2020Leveraging Abstract Meaning Representation for Knowledge Base Question Answeringcited by 53
  17. 2023FlexKBQA: A Flexible LLM-Powered Framework for Few-Shot Knowledge Base Question Answeringcited by 51
  18. 2024DALK: Dynamic Co-Augmentation of LLMs and KG to answer Alzheimer's Disease Questions with Scientific Literaturecited by 50
  19. 2023Making Large Language Models Perform Better in Knowledge Graph Completioncited by 48
  20. 2023ChatKBQA: A Generate-then-Retrieve Framework for Knowledge Base Question Answering with Fine-tuned Large Language Modelscited by 44
  21. 2024How Easily do Irrelevant Inputs Skew the Responses of Large Language Models?cited by 44
  22. 2024Knowledge Graph Enhanced Large Language Model Editingcited by 38
  23. 2023CodeKGC: Code Language Model for Generative Knowledge Graph Constructioncited by 28
  24. 2023Complex Logical Reasoning over Knowledge Graphs using Large Language Modelscited by 28
  25. 2021DISCOS: Bridging the Gap between Discourse Knowledge and Commonsense Knowledgecited by 26
  26. 2020A Simple Yet Strong Pipeline for HotpotQAcited by 24
  27. 2021Conversational Question Answering over Knowledge Graphs with Transformer and Graph Attention Networkscited by 24
  28. 2022Knowledge Base Question Answering: A Semantic Parsing Perspectivecited by 22
  29. 2023A Universal Question-Answering Platform for Knowledge Graphscited by 17
  30. 2024Efficient Knowledge Infusion via KG-LLM Alignmentcited by 13
  31. 2022Overview of BioASQ 2022: The tenth BioASQ challenge on Large-Scale Biomedical Semantic Indexing and Question Answeringcited by 9
  32. 2023Evaluating the Knowledge Base Completion Potential of GPTcited by 9
  33. 2020Chinese Medical Question Answer Matching Based on Interactive Sentence Representation Learningcited by 6
  34. 2024IEPile: Unearthing Large-Scale Schema-Based Information Extraction Corpuscited by 5
  35. 2023Commonsense Knowledge Graph Completion Via Contrastive Pretraining and Node Clusteringcited by 4
  36. 2024Integrating Multi-Head Convolutional Encoders with Cross-Attention for Improved SPARQL Query Translationcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 37; 2026: 27.

67 papers.

Sort:

By area:

  1. 2025A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Modelscited by 85
  2. 2025Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learningcited by 50
  3. 2025LinearRAG: Linear Graph Retrieval Augmented Generation on Large-scale Corporacited by 47
  4. 2025Retrieval-Augmented Generation with Hierarchical Knowledgecited by 46
  5. 2025When to use Graphs in RAG: A Comprehensive Analysis for Graph Retrieval-Augmented Generationcited by 46
  6. 2025GFM-RAG: Graph Foundation Model for Retrieval Augmented Generationcited by 40
  7. 2025A Survey on Knowledge-Oriented Retrieval-Augmented Generationcited by 34
  8. 2025R&D-Agent: An LLM-Agent Framework Towards Autonomous Data Sciencecited by 33
  9. 2025Large Language Models Meet Knowledge Graphs for Question Answering: Synthesis and Opportunitiescited by 30
  10. 2025AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corporacited by 23
  11. 2024GeAR: Graph-enhanced Agent for Retrieval-augmented Generationcited by 17
  12. 2025LeanRAG: Knowledge-Graph-Based Generation with Semantic Aggregation and Hierarchical Retrievalcited by 14
38 more
  1. 2025ReAgent: Reversible Multi-Agent Reasoning for Knowledge-Enhanced Multi-Hop QAcited by 12
  2. 2025CoAT: Chain-of-Associated-Thoughts Framework for Enhancing Large Language Models Reasoningcited by 11
  3. 2025ReMindRAG: Low-Cost LLM-Guided Knowledge Graph Traversal for Efficient RAGcited by 8
  4. 2024LEGO-GraphRAG: Modularizing Graph-based Retrieval-Augmented Generation for Design Space Explorationcited by 7
  5. 2025Reason-Align-Respond: Aligning LLM Reasoning with Knowledge Graphs for KGQAcited by 7
  6. 2025TeaRAG: A Token-Efficient Agentic Retrieval-Augmented Generation Frameworkcited by 7
  7. 2025AGRAG: Advanced Graph-based Retrieval-Augmented Generation for LLMscited by 7
  8. 2025How to Mitigate Information Loss in Knowledge Graphs for GraphRAG: Leveraging Triple Context Restoration and Query-Driven Feedbackcited by 6
  9. 2025Knowledge Augmented Complex Problem Solving with Large Language Models: A Surveycited by 6
  10. 2025AI-Powered Math Tutoring: Platform for Personalized and Adaptive Educationcited by 6
  11. 2025Thinker: Training LLMs in Hierarchical Thinking for Deep Search via Multi-Turn Interactioncited by 5
  12. 2025Cross-Granularity Hypergraph Retrieval-Augmented Generation for Multi-hop Question Answeringcited by 4
  13. 2025MultiRAG: A Knowledge-guided Framework for Mitigating Hallucination in Multi-source Retrieval Augmented Generationcited by 3
  14. 2026Agents-K1: Towards Agent-native Knowledge Orchestrationcited by 3
  15. 2025ROGRAG: A Robustly Optimized GraphRAG Frameworkcited by 2
  16. 2025XGraphRAG: Interactive Visual Analysis for Graph-based Retrieval-Augmented Generationcited by 2
  17. 2025KAG-Thinker: Interactive Thinking and Deep Reasoning in LLMs via Knowledge-Augmented Generationcited by 2
  18. 2025DF-LLaVA: Unlocking MLLMs for Synthetic Image Detection via Knowledge Injection and Conflict-Driven Self-Reflectioncited by 2
  19. 2025HyperbolicRAG: Enhancing Retrieval-Augmented Generation with Hyperbolic Representationscited by 2
  20. 2026Tackling the Inherent Difficulty of Noise Filtering in RAGcited by 2
  21. 2026Structure Guided Retrieval-Augmented Generation for Factual Queriescited by 2
  22. 2026REAL: A Reasoning-Enhanced Graph Framework for Long-Term Memory Management of LLMscited by 2
  23. 2024Extracting effective solutions hidden in large language models via generated comprehensive specialists: case studies in developing electronic devicescited by 1
  24. 2025DeepWriter: A Fact-Grounded Multimodal Writing Assistant Based On Offline Knowledge Basecited by 1
  25. 2025SKA-Bench: A Fine-Grained Benchmark for Evaluating Structured Knowledge Understanding of LLMscited by 1
  26. 2025When Retrieval Succeeds and Fails: Rethinking Retrieval-Augmented Generation for LLMscited by 1
  27. 2025Cross-modal Retrieval Models for Stripped Binary Analysiscited by 1
  28. 2025LexRel: Benchmarking Legal Relation Extraction for Chinese Civil Casescited by 1
  29. 2026Disco-RAG: Discourse-Aware Retrieval-Augmented Generationcited by 1
  30. 2026VISTA: Knowledge-Driven Vessel Trajectory Imputation with Repair Provenancecited by 1
  31. 2026When to Trust: A Causality-Aware Calibration Framework for Accurate Knowledge Graph Retrieval-Augmented Generationcited by 1
  32. 2026MED-COPILOT: A Medical Assistant Powered by GraphRAG and Similar Patient Case Retrievalcited by 1
  33. 2026Toward Robust GraphRAG: Mitigating Retrieval Drift and Hallucination from Imperfect Knowledge Graphscited by 1
  34. 2026Embodied Science: Closing the Discovery Loop with Agentic Embodied AIcited by 1
  35. 2026Towards Automatic Soccer Commentary Generation with Knowledge-Enhanced Visual Reasoningcited by 1
  36. 2026ContextRAG: Extraction-Free Hierarchical Graph Construction for Retrieval-Augmented Generationcited by 1
  37. 2026MC-RAG System: A Structure-Driven RAG System for Multi-Constraint Queriescited by 1
  38. 2025ThinkTank: A Framework for Generalizing Domain-Specific AI Agent Systems into Universal Collaborative Intelligence Platformscited by 0

50 most cited of 67 All 67 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025FRAG: A Flexible Modular Framework for Retrieval-Augmented Generation based on Knowledge Graphs
  2. 2026UltRAG: a Universal Simple Scalable Recipe for Knowledge Graph RAG
  3. 2025RAKG:Document-level Retrieval Augmented Knowledge Graph Construction
  4. 2025Enhancing Large Language Models (LLMs) for Telecommunications using Knowledge Graphs and Retrieval-Augmented Generation
  5. 2024Domain-Specific Retrieval-Augmented Generation Using Vector Stores, Knowledge Graphs, and Tensor Factorization
  6. 2025KERAG: Knowledge-Enhanced Retrieval-Augmented Generation for Advanced Question Answering
  7. 2024Knowledge Pyramid Construction for Multi-Level Retrieval-Augmented Generation
  8. 2025Evaluating Knowledge Graph Based Retrieval Augmented Generation Methods under Knowledge Incompleteness