mlsanityData to 14 Oct 2026

KG-RAG: Bridging the Gap Between Knowledge and Creativity

arXiv 2405.12035 ↗First posted 20 May 2024cs.AI cs.CL cs.IRcited by 56

On the map: Retrieval-augmented generation → Agentic RAG, agents and memory

also in 1 more
Abstract (arXiv)

Ensuring factual accuracy while maintaining the creative capabilities of Large Language Model Agents (LMAs) poses significant challenges in the development of intelligent agent systems. LMAs face prevalent issues such as information hallucinations, catastrophic forgetting, and limitations in processing long contexts when dealing with knowledge-intensive tasks. This paper introduces a KG-RAG (Knowledge Graph-Retrieval Augmented Generation) pipeline, a novel framework designed to enhance the knowledge capabilities of LMAs by integrating structured Knowledge Graphs (KGs) with the functionalities of LLMs, thereby significantly reducing the reliance on the latent knowledge of LLMs. The KG-RAG pipeline constructs a KG from unstructured text and then performs information retrieval over the newly created graph to perform KGQA (Knowledge Graph Question Answering). The retrieval methodology leverages a novel algorithm called Chain of Explorations (CoE) which benefits from LLMs reasoning to explore nodes and relationships within the KG sequentially. Preliminary experiments on the ComplexWebQuestions dataset demonstrate notable improvements in the reduction of hallucinated content and suggest a promising path toward developing intelligent systems adept at handling knowledge-intensive tasks.

Key facts. Cited by 56 papers in the map (data through 14 Oct 2026). Placed in Agentic RAG, agents and memory, one of 15 directions in Retrieval-augmented generation. Builds on 52 of its 67 references that are in the map. First posted on arXiv 20 May 2024.

Builds on

52 of 67 references.

References · 52

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  4. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  5. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  6. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,148
  7. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  8. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  9. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,234
  10. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  11. 2022Survey of Hallucination in Natural Language Generationcited by 2,075
  12. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,439
38 more
  1. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,332
  2. 2020Oscar: Object-Semantics Aligned Pre-training for Vision-Language Taskscited by 1,214
  3. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Modelscited by 886
  4. 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 698
  5. 2023Unifying Large Language Models and Knowledge Graphs: A Roadmapcited by 668
  6. 2023An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuningcited by 639
  7. 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 517
  8. 2018The Web as a Knowledge-base for Answering Complex Questionscited by 410
  9. 2023Augmented Language Models: a Surveycited by 403
  10. 2023StructGPT: A General Framework for Large Language Model to Reason over Structured Datacited by 343
  11. 2023Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoningcited by 328
  12. 2023MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoningcited by 316
  13. 2024MM-LLMs: Recent Advances in MultiModal Large Language Modelscited by 278
  14. 2023Can Language Models Solve Graph Problems in Natural Language?cited by 252
  15. 2024G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answeringcited by 223
  16. 2023Large Language Models on Graphs: A Comprehensive Surveycited by 192
  17. 2023Fine-Tuning or Retrieval? Comparing Knowledge Injection in LLMscited by 178
  18. 2023ChatDB: Augmenting LLMs with Databases as Their Symbolic Memorycited by 140
  19. 2015Large-scale Simple Question Answering with Memory Networkscited by 127
  20. 2023Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sourcescited by 122
  21. 2020A Survey of Knowledge-Enhanced Text Generationcited by 120
  22. 2023GraphLLM: Boosting Graph Reasoning Ability of Large Language Modelcited by 107
  23. 2017Joint Extraction of Entities and Relations Based on a Novel Tagging Schemecited by 102
  24. 2023LLMs for Knowledge Graph Construction and Reasoning: Recent Capabilities and Future Opportunitiescited by 97
  25. 2023A Survey of Graph Meets Large Language Model: Progress and Future Directionscited by 85
  26. 2020Domain-specific Knowledge Graphs: A surveycited by 68
  27. 2021ExplaGraphs: An Explanation Graph Generation Task for Structured Commonsense Reasoningcited by 58
  28. 2020More Data, More Relations, More Context and More Openness: A Review and Outlook for Relation Extractioncited by 52
  29. 2023Thought Propagation: An Analogical Approach to Complex Reasoning with Large Language Modelscited by 37
  30. 2024Towards Optimizing the Costs of LLM Usagecited by 33
  31. 2016CoType: Joint Extraction of Typed Entities and Relations with Knowledge Basescited by 28
  32. 2020(Almost) All of Entity Resolutioncited by 23
  33. 2021Entity Linking Meets Deep Learning: Techniques and Solutionscited by 22
  34. 2021End-to-End NLP Knowledge Graph Constructioncited by 21
  35. 2023Graph Meets LLMs: Towards Large Graph Modelscited by 20
  36. 2023Integrating Graphs with Large Language Models: Methods and Prospectscited by 18
  37. 2022Nebula Graph: An open source distributed graph databasecited by 8
  38. 2022A Study on the Efficiency and Generalization of Light Hybrid Retrieverscited by 7

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 14; 2025: 31; 2026: 11.

56 papers.

Sort:

By area:

  1. 2024Retrieval-Augmented Generation with Graphs (GraphRAG)cited by 172
  2. 2025A Survey on Knowledge-Oriented Retrieval-Augmented Generationcited by 36
  3. 2025Large Language Models Meet Knowledge Graphs for Question Answering: Synthesis and Opportunitiescited by 31
  4. 2025NodeRAG: Structuring Graph-based RAG with Heterogeneous Nodescited by 26
  5. 2024HyPA-RAG: A Hybrid Parameter Adaptive Retrieval-Augmented Generation System for AI Legal and Policy Applicationscited by 22
  6. 2025Large language models for artificial general intelligence (AGI): A survey of foundational principles and approachescited by 18
  7. 2024TRACE the Evidence: Constructing Knowledge-Grounded Reasoning Chains for Retrieval-Augmented Generationcited by 16
  8. 2024Domain-Specific Retrieval-Augmented Generation Using Vector Stores, Knowledge Graphs, and Tensor Factorizationcited by 15
  9. 2024Logical Consistency of Large Language Models in Fact-checkingcited by 15
  10. 2024KG-Retriever: Efficient Knowledge Indexing for Retrieval-Augmented Large Language Modelscited by 12
  11. 2025Agentic Medical Knowledge Graphs Enhance Medical Question Answering: Bridging the Gap Between LLMs and Evolving Medical Knowledgecited by 12
  12. 2025AgriGPT: a Large Language Model Ecosystem for Agriculturecited by 11
38 more
  1. 2024Language Modeling with Editable External Knowledgecited by 9
  2. 2025RAG-KG-IL: A Multi-Agent Hybrid Framework for Reducing Hallucinations and Enhancing LLM Reasoning through RAG and Incremental Knowledge Graph Learning Integrationcited by 9
  3. 2025Graph-Augmented Reasoning: Evolving Step-by-Step Knowledge Graph Retrieval for LLM Reasoningcited by 8
  4. 2025A Survey on Retrieval And Structuring Augmented Generation with Large Language Modelscited by 8
  5. 2025Can Knowledge-Graph-based Retrieval Augmented Generation Really Retrieve What You Need?cited by 8
  6. 2025Towards Global Retrieval Augmented Generation: A Benchmark for Corpus-Level Reasoningcited by 8
  7. 2024Rx Strategist: Prescription Verification using LLM Agents Systemcited by 7
  8. 2025Loki's Dance of Illusions: A Comprehensive Survey of Hallucination in Large Language Modelscited by 7
  9. 2024Multi-Document Financial Question Answering using LLMscited by 6
  10. 2025Incorporating Legal Structure in Retrieval-Augmented Generation: A Case Study on Copyright Fair Usecited by 6
  11. 2025MAGIC: A Multi-Hop and Graph-Based Benchmark for Inter-Context Conflicts in Retrieval-Augmented Generationcited by 6
  12. 2025Reasoning by Exploration: A Unified Approach to Retrieval and Generation over Graphscited by 6
  13. 2025MARAG-R1: Beyond Single Retriever via Reinforcement-Learned Multi-Tool Agentic Retrievalcited by 5
  14. 2024Retrieval-Augmented Feature Generation for Domain-Specific Classificationcited by 3
  15. 2024CodeRefine: A Pipeline for Enhancing LLM-Generated Code Implementations of Research Paperscited by 3
  16. 2024LLM+KG@VLDB'24 Workshop Summarycited by 3
  17. 2026S-Path-RAG: Semantic-Aware Shortest-Path Retrieval Augmented Generation for Multi-Hop Knowledge Graph Question Answeringcited by 3
  18. 2026NeocorRAG: Less Irrelevant Information, More Explicit Evidence, and More Effective Recall via Evidence Chainscited by 3
  19. 2025MultiHal: Multilingual Dataset for Knowledge-Graph Grounded Evaluation of LLM Hallucinationscited by 2
  20. 2025Adaptive and Resource-efficient Agentic AI Systems for Mobile and Embedded Devices: A Surveycited by 2
  21. 2025DPRM: A Dual Implicit Process Reward Model in Multi-Hop Question Answeringcited by 2
  22. 2024DynaGRAG | Exploring the Topology of Information for Advancing Language Understanding and Generation in Graph Retrieval-Augmented Generationcited by 1
  23. 2025Transformer-Based Multimodal Knowledge Graph Completion with Link-Aware Contextscited by 1
  24. 2025Improving TCM Question Answering through Tree-Organized Self-Reflective Retrieval with LLMscited by 1
  25. 2025Follow the Path: Reasoning over Knowledge Graph Paths to Improve Large Language Model Factualitycited by 1
  26. 2025HeTa: Relation-wise Heterogeneous Graph Foundation Attack Modelcited by 1
  27. 2025Knowledge Fusion via Bidirectional Information Aggregationcited by 1
  28. 2025Ontology-Enhanced Knowledge Graph Completion using Large Language Modelscited by 1
  29. 2025CLARIFY: A Specialist-Generalist Framework for Accurate and Lightweight Dermatological Visual Question Answeringcited by 1
  30. 2026Disco-RAG: Discourse-Aware Retrieval-Augmented Generationcited by 1
  31. 2026MED-COPILOT: A Medical Assistant Powered by GraphRAG and Similar Patient Case Retrievalcited by 1
  32. 2026Metadata, Structure, or Strategy? A Decomposition of RAG Context Enrichmentcited by 1
  33. 2024Leveraging Retrieval-Augmented Generation for Persian University Knowledge Retrievalcited by 0
  34. 2025Beyond Single Pass, Looping Through Time: KG-IRAG with Iterative Knowledge Retrievalcited by 0
  35. 2025SlimRAG: Retrieval without Graphs via Entity-Aware Context Selectioncited by 0
  36. 2025RDMA: Cost Effective Agent-Driven Rare Disease Mining from Electronic Health Recordscited by 0
  37. 2025GOSU: Retrieval-Augmented Generation with Global-Level Optimized Semantic Unit-Centric Frameworkcited by 0
  38. 2025GRPO++: Enhancing Dermatological Reasoning under Low Resource Settingscited by 0

50 most cited of 56 All 56 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Efficient and Transferable Agentic Knowledge Graph RAG via Reinforcement Learning
  2. 2025KIMAs: A Configurable Knowledge Integrated Multi-Agent System
  3. 2024KG-Agent: An Efficient Autonomous Agent Framework for Complex Reasoning over Knowledge Graph
  4. 2025Towards Open-World Retrieval-Augmented Generation on Knowledge Graph: A Multi-Agent Collaboration Framework
  5. 2026KG2Code: Bridging Knowledge Graphs and Large Language Models via Executable Code for Question Answering
  6. 2025CoCoA: Collaborative Chain-of-Agents for Parametric-Retrieved Knowledge Synergy
  7. 2025Agentic RAG with Knowledge Graphs for Complex Multi-Hop Reasoning in Real-World Applications
  8. 2025RAGCap-Bench: Benchmarking Capabilities of LLMs in Agentic Retrieval Augmented Generation Systems