mlsanityData to 7 Oct 2026

Simple Is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation

arXiv 2410.20724 ↗First posted 28 Oct 2024cs.CL cs.IR cs.LGcited by 78

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

also in 1 more
Abstract (arXiv)

Large Language Models (LLMs) demonstrate strong reasoning abilities but face limitations such as hallucinations and outdated knowledge. Knowledge Graph (KG)-based Retrieval-Augmented Generation (RAG) addresses these issues by grounding LLM outputs in structured external knowledge from KGs. However, current KG-based RAG frameworks still struggle to optimize the trade-off between retrieval effectiveness and efficiency in identifying a suitable amount of relevant graph information for the LLM to digest. We introduce SubgraphRAG, extending the KG-based RAG framework that retrieves subgraphs and leverages LLMs for reasoning and answer prediction. Our approach innovatively integrates a lightweight multilayer perceptron with a parallel triple-scoring mechanism for efficient and flexible subgraph retrieval while encoding directional structural distances to enhance retrieval effectiveness. The size of retrieved subgraphs can be flexibly adjusted to match the query's need and the downstream LLM's capabilities. This design strikes a balance between model complexity and reasoning power, enabling scalable and generalizable retrieval processes. Notably, based on our retrieved subgraphs, smaller LLMs like Llama3.1-8B-Instruct deliver competitive results with explainable reasoning, while larger models like GPT-4o achieve state-of-the-art accuracy compared with previous baselines -- all without fine-tuning. Extensive evaluations on the WebQSP and CWQ benchmarks highlight SubgraphRAG's strengths in efficiency, accuracy, and reliability by reducing hallucinations and improving response grounding.

Key facts. Cited by 78 papers in the map (data through 7 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 68 of its 84 references that are in the map. First posted on arXiv 28 Oct 2024.

Builds on

68 of 84 references.

Closest ancestors · 12

Same direction, newest first

  1. 2024Dual Reasoning: A GNN-LLM Collaborative Framework for Knowledge Graph Question Answering3 Jun
  2. 2024GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoning30 May
  3. 2024Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphs10 Apr
  4. 2024KG-Agent: An Efficient Autonomous Agent Framework for Complex Reasoning over Knowledge Graph17 Feb
  5. 2023KnowledgeNavigator: Leveraging Large Language Models for Enhanced Reasoning over Knowledge Graph26 Dec
  6. 2023Retrieval-Augmented Generation for Large Language Models: A Survey18 Dec
  7. 2023KG-GPT: A General Framework for Reasoning on Knowledge Graphs Using Large Language Models17 Oct
  8. 2023Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning2 Oct
  9. 2023MindMap: Knowledge Graph Prompting Sparks Graph of Thoughts in Large Language Models17 Aug
  10. 2023Graph Reasoning for Question Answering with Triplet Retrieval30 May
  11. 2023GrapeQA: GRaph Augmentation and Pruning to Enhance Question-Answering22 Mar
  12. 2022UniKGQA: Unified Retrieval and Reasoning for Solving Multi-hop Question Answering Over Knowledge Graph2 Dec

Other references · 56

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2024The Llama 3 Herd of Modelscited by 14,192
  5. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  6. 2017Inductive Representation Learning on Large Graphscited by 6,284
  7. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  8. 2018How Powerful are Graph Neural Networks?cited by 4,355
  9. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  10. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  11. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  12. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
38 more
  1. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,579
  2. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
  3. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  4. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,582
  5. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,411
  6. 2016Variational Graph Auto-Encoderscited by 1,373
  7. 2023Towards General Text Embeddings with Multi-stage Contrastive Learningcited by 705
  8. 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 695
  9. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 691
  10. 2023Unifying Large Language Models and Knowledge Graphs: A Roadmapcited by 663
  11. 2022MTEB: Massive Text Embedding Benchmarkcited by 623
  12. 2022Towards Reasoning in Large Language Models: A Surveycited by 593
  13. 2018The Web as a Knowledge-base for Answering Complex Questionscited by 409
  14. 2021QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answeringcited by 386
  15. 2023StructGPT: A General Framework for Large Language Model to Reason over Structured Datacited by 339
  16. 2024Graph Retrieval-Augmented Generation: A Surveycited by 320
  17. 2023FreshLLMs: Refreshing Large Language Models with Search Engine Augmentationcited by 308
  18. 2021Time-Aware Language Models as Temporal Knowledge Basescited by 290
  19. 2022RealTime QA: What's the Answer Right Now?cited by 239
  20. 2020Can Graph Neural Networks Count Substructures?cited by 235
  21. 2024G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answeringcited by 217
  22. 2019KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoningcited by 216
  23. 2019TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agentscited by 188
  24. 2019PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Textcited by 182
  25. 2018Open Domain Question Answering Using Early Fusion of Knowledge Bases and Textcited by 167
  26. 2023Knowledge Graph Prompting for Multi-Document Question Answeringcited by 150
  27. 2017Know-Evolve: Deep Temporal Reasoning for Dynamic Knowledge Graphscited by 149
  28. 2020Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learningcited by 148
  29. 2023Retrieval meets Long Context Large Language Modelscited by 114
  30. 2022A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multimodalcited by 106
  31. 2021Improving Multi-hop Knowledge Base Question Answering by Learning Intermediate Supervision Signalscited by 100
  32. 2023Knowledge-Driven CoT: Exploring Faithful Reasoning in LLMs for Knowledge-intensive Question Answeringcited by 97
  33. 2024CRAG -- Comprehensive RAG Benchmarkcited by 94
  34. 2022Subgraph Retrieval Enhanced Model for Multi-hop Knowledge Base Question Answeringcited by 93
  35. 2024GRAG: Graph Retrieval-Augmented Generationcited by 77
  36. 2023Retrieve-Rewrite-Answer: A KG-to-Text Enhanced LLMs Framework for Knowledge Graph Question Answeringcited by 64
  37. 2023Are ChatGPT and GPT-4 General-Purpose Solvers for Financial Text Analytics? A Study on Several Typical Taskscited by 59
  38. 2023Knowledge Graph-Augmented Language Models for Knowledge-Grounded Dialogue Generationcited by 54

50 most cited of 56 All 56 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 40; 2026: 35.

78 papers.

Sort:

By area:

  1. 2024Retrieval-Augmented Generation with Graphs (GraphRAG)cited by 170
  2. 2025A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Modelscited by 85
  3. 2025VideoRAG: Retrieval-Augmented Generation with Extreme Long-Context Videoscited by 76
  4. 2025PathRAG: Pruning Graph-based Retrieval Augmented Generation with Relational Pathscited by 60
  5. 2025GFM-RAG: Graph Foundation Model for Retrieval Augmented Generationcited by 40
  6. 2025Vgent: Graph-based Retrieval-Reasoning-Augmented Generation For Long Video Understandingcited by 30
  7. 2025MiniRAG: Towards Extremely Simple Retrieval-Augmented Generationcited by 28
  8. 2025Graphs Meet AI Agents: Taxonomy, Progress, and Future Opportunitiescited by 23
  9. 2025RAG over Tables: Hierarchical Memory Index, Multi-Stage Retrieval, and Benchmarkingcited by 17
  10. 2025MMGraphRAG: Bridging Vision and Language with Interpretable Multimodal Knowledge Graphscited by 16
  11. 2024KG-Retriever: Efficient Knowledge Indexing for Retrieval-Augmented Large Language Modelscited by 12
  12. 2025Diagnosing and Addressing Pitfalls in KG-RAG Datasets: Toward More Reliable Benchmarkingcited by 11
38 more
  1. 2025Reliable Reasoning Path: Distilling Effective Guidance for LLM Reasoning with Knowledge Graphscited by 9
  2. 2025Evaluating Knowledge Graph Based Retrieval Augmented Generation Methods under Knowledge Incompletenesscited by 7
  3. 2026Query-Aware Flow Diffusion for Graph-Based RAG with Retrieval Guaranteescited by 7
  4. 2025DAMR: Efficient and Adaptive Context-Aware Knowledge Graph Question Answering with LLM-Guided MCTScited by 6
  5. 2025AutoGraph-R1: End-to-End Reinforcement Learning for Knowledge Graph Constructioncited by 6
  6. 2026A2RAG: Adaptive Agentic Graph Retrieval for Cost-Aware and Reliable Reasoningcited by 6
  7. 2025GraphRAFT: Retrieval Augmented Fine-Tuning for Knowledge Graphs on Graph Databasescited by 5
  8. 2025Learning Efficient and Generalizable Graph Retriever for Knowledge-Graph Question Answeringcited by 5
  9. 2025Reasoning by Exploration: A Unified Approach to Retrieval and Generation over Graphscited by 5
  10. 2025Search-on-Graph: Iterative Informed Navigation for Large Language Model Reasoning on Knowledge Graphscited by 5
  11. 2025PolyG: Adaptive Graph Traversal for Diverse GraphRAG Questionscited by 4
  12. 2025FG-RAG: Enhancing Query-Focused Summarization with Context-Aware Fine-Grained Graph RAGcited by 4
  13. 2025Explainable Knowledge Graph Retrieval-Augmented Generation (KG-RAG) with KG-SMILEcited by 4
  14. 2025LOGicalThought: Logic-Based Ontological Grounding of LLMs for High-Assurance Reasoningcited by 4
  15. 2025Last Layer Logits to Logic: Empowering LLMs with Logic-Consistent Structured Knowledge Reasoningcited by 4
  16. 2025Weak-to-Strong GraphRAG: Aligning Weak Retrievers with Large Language Models for Graph-based Retrieval Augmented Generationcited by 3
  17. 2025ProgRAG: Hallucination-Resistant Progressive Retrieval and Reasoning over Knowledge Graphscited by 3
  18. 2025KBQA-R1: Reinforcing Large Language Models for Knowledge Base Question Answeringcited by 3
  19. 2026NeuroSymActive: Differentiable Neural-Symbolic Reasoning with Active Exploration for Knowledge Graph Question Answeringcited by 3
  20. 2026Agentic SPARQL: Evaluating SPARQL-MCP-powered Intelligent Agents on the Federated KGQA Benchmarkcited by 3
  21. 2026S-Path-RAG: Semantic-Aware Shortest-Path Retrieval Augmented Generation for Multi-Hop Knowledge Graph Question Answeringcited by 3
  22. 2026Agents-K1: Towards Agent-native Knowledge Orchestrationcited by 3
  23. 2025Large Language models for Time Series Analysis: Techniques, Applications, and Challengescited by 2
  24. 2025Ground-Truth Subgraphs for Better Training and Evaluation of Knowledge Graph Augmented LLMscited by 2
  25. 2025DPRM: A Dual Implicit Process Reward Model in Multi-Hop Question Answeringcited by 2
  26. 2025Cooperative Retrieval-Augmented Generation for Question Answering: Mutual Information Exchange and Ranking by Contrasting Layerscited by 2
  27. 2026KLDrive: Fine-Grained 3D Scene Reasoning for Autonomous Driving based on Knowledge Graphcited by 2
  28. 2026Evaluating Relational Reasoning in LLMs with RELcited by 2
  29. 2026Teaching LLMs to See Graphs: Unifying Text and Structural Reasoningcited by 2
  30. 2026SAGE: A Self-Evolving Agentic Graph-Memory Engine for Structure-Aware Associative Memorycited by 2
  31. 2024A Comprehensive Framework for Reliable Legal AI: Combining Specialized Expert Systems and Adaptive Refinementcited by 1
  32. 2025Human Cognition Inspired RAG with Knowledge Graph for Complex Problem Solvingcited by 1
  33. 2025Exemplar-Guided Planing: Enhanced LLM Agent for KGQAcited by 1
  34. 2025Think Parallax: Solving Multi-Hop Problems via Multi-View Knowledge-Graph-Based Retrieval-Augmented Generationcited by 1
  35. 2025Detecting Hallucinations in Graph Retrieval-Augmented Generation via Attention Patterns and Semantic Alignmentcited by 1
  36. 2026Toward Robust GraphRAG: Mitigating Retrieval Drift and Hallucination from Imperfect Knowledge Graphscited by 1
  37. 2026GraphWalk: Enabling Reasoning in Large Language Models through Tool-Based Graph Navigationcited by 1
  38. 2026MG2-RAG: Multi-Granularity Graph for Multimodal Retrieval-Augmented Generationcited by 1

50 most cited of 78 All 78 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025GRIL: Knowledge Graph Retrieval-Integrated Learning with Large Language Models
  2. 2024Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation
  3. 2025FRAG: A Flexible Modular Framework for Retrieval-Augmented Generation based on Knowledge Graphs
  4. 2025Graph-based Approaches and Functionalities in Retrieval-Augmented Generation: A Comprehensive Survey
  5. 2025You Don't Need Pre-built Graphs for RAG: Retrieval Augmented Generation with Adaptive Reasoning Structures
  6. 2024SimGRAG: Leveraging Similar Subgraphs for Knowledge Graphs Driven Retrieval-Augmented Generation
  7. 2024Less is More: Making Smaller Language Models Competent Subgraph Retrievers for Multi-hop KGQA
  8. 2025A Query-Aware Multi-Path Knowledge Graph Fusion Approach for Enhancing Retrieval-Augmented Generation in Large Language Models