mlsanityData to 14 Oct 2026

Large Language Models Meet Knowledge Graphs for Question Answering: Synthesis and Opportunities

arXiv 2505.20099 ↗First posted 26 May 2025cs.CL cs.AI cs.IRcited by 31

Not on the map. Why?

Abstract (arXiv)

Large language models (LLMs) have demonstrated remarkable performance on question-answering (QA) tasks because of their superior capabilities in natural language understanding and generation. However, LLM-based QA struggles with complex QA tasks due to poor reasoning capacity, outdated knowledge, and hallucinations. Several recent works synthesize LLMs and knowledge graphs (KGs) for QA to address the above challenges. In this survey, we propose a new structured taxonomy that categorizes the methodology of synthesizing LLMs and KGs for QA according to the categories of QA and the KG's role when integrating with LLMs. We systematically survey state-of-the-art methods in synthesizing LLMs and KGs for QA and compare and analyze these approaches in terms of strength, limitations, and KG requirements. We then align the approaches with QA and discuss how these approaches address the main challenges of different complex QA. Finally, we summarize the advancements, evaluation metrics, and benchmark datasets and highlight open challenges and opportunities.

Key facts. Cited by 31 papers in the map (data through 14 Oct 2026). Builds on 64 of its 102 references that are in the map. First posted on arXiv 26 May 2025.

Builds on

64 of 102 references.

References · 64

  1. 2022Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answeringcited by 1,919
  2. 2018CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledgecited by 1,822
  3. 2020What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Examscited by 1,356
  4. 2023Unifying Large Language Models and Knowledge Graphs: A Roadmapcited by 668
  5. 2024Graph Retrieval-Augmented Generation: A Surveycited by 324
  6. 2020Generation-Augmented Retrieval for Open-domain Question Answeringcited by 186
  7. 2022GreaseLM: Graph REASoning Enhanced Language Models for Question Answeringcited by 171
  8. 2022Deep Bidirectional Language-Knowledge Graph Pretrainingcited by 156
  9. 2023Knowledge Graph Prompting for Multi-Document Question Answeringcited by 152
  10. 2024Evaluation of Retrieval-Augmented Generation: A Surveycited by 146
  11. 2021SituatedQA: Incorporating Extra-Linguistic Contexts into QAcited by 145
  12. 2024Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QAcited by 122
38 more
  1. 2024Retrieval-Augmented Generation with Knowledge Graphs for Customer Service Question Answeringcited by 96
  2. 2024KG-Agent: An Efficient Autonomous Agent Framework for Complex Reasoning over Knowledge Graphcited by 93
  3. 2025MedRAG: Enhancing Retrieval-augmented Generation with Knowledge Graph-Elicited Reasoning for Healthcare Copilotcited by 83
  4. 2024Plan-on-Graph: Self-Correcting Adaptive Planning of Large Language Model on Knowledge Graphscited by 78
  5. 2023Mitigating Large Language Model Hallucinations via Autonomous Knowledge Graph-based Retrofittingcited by 70
  6. 2021Complex Temporal Question Answering on Knowledge Graphscited by 69
  7. 2024KAG: Boosting LLMs in Professional Domains via Knowledge Augmented Generationcited by 67
  8. 2024KG-RAG: Bridging the Gap Between Knowledge and Creativitycited by 56
  9. 2025Injecting Domain-Specific Knowledge into Large Language Models: A Comprehensive Surveycited by 51
  10. 2024LongRAG: A Dual-Perspective Retrieval-Augmented Generation Paradigm for Long-Context Question Answeringcited by 49
  11. 2024VisDoM: Multi-Document QA with Visually Rich Elements Using Multimodal Retrieval-Augmented Generationcited by 41
  12. 2024KG-Rank: Enhancing Large Language Models for Medical QA with Knowledge Graphs and Ranking Techniquescited by 37
  13. 2023TempTabQA: Temporal Question Answering for Semi-Structured Tablescited by 27
  14. 2024M3SciQA: A Multi-Modal Multi-Document Scientific QA Benchmark for Evaluating Foundation Modelscited by 27
  15. 2024Does RAG Introduce Unfairness in LLMs? Evaluating Fairness in Retrieval-Augmented Generation Systemscited by 26
  16. 2025NodeRAG: Structuring Graph-based RAG with Heterogeneous Nodescited by 26
  17. 2023A Benchmark to Understand the Role of Knowledge Graphs on Large Language Model's Accuracy for Question Answering on Enterprise SQL Databasescited by 25
  18. 2024HOLMES: Hyper-Relational Knowledge Graphs for Multi-hop Question Answering using LLMscited by 24
  19. 2024Learning to Plan for Retrieval-Augmented Large Language Models from Knowledge Graphscited by 24
  20. 2024Can Knowledge Graphs Make Large Language Models More Trustworthy? An Empirical Study Over Open-ended Question Answeringcited by 24
  21. 2024InfuserKI: Enhancing Large Language Models with Knowledge Graphs via Infuser-Guided Knowledge Integrationcited by 19
  22. 2024LLM-Based Multi-Hop Question Answering with Knowledge Graph Integration in Evolving Environmentscited by 18
  23. 2025PIKE-RAG: sPecIalized KnowledgE and Rationale Augmented Generationcited by 18
  24. 2024StraGo: Harnessing Strategic Guidance for Prompt Optimizationcited by 17
  25. 2023keqing: knowledge-based question answering is a nature chain-of-thought mentor of LLMcited by 16
  26. 2024PAT-Questions: A Self-Updating Benchmark for Present-Anchored Temporal Question-Answeringcited by 15
  27. 2025Knowledge Graph-extended Retrieval Augmented Generation for Question Answeringcited by 14
  28. 2023Developing a Scalable Benchmark for Assessing Large Language Models in Knowledge Graph Engineeringcited by 13
  29. 2024Empowering Large Language Models to Set up a Knowledge Retrieval Indexer via Self-Learningcited by 13
  30. 2024Question-guided Knowledge Graph Re-scoring and Injection for Knowledge Graph Question Answeringcited by 13
  31. 2024Graph of Records: Boosting Retrieval Augmented Generation for Long-context Summarization with Graphscited by 12
  32. 2023Reasoning over Hierarchical Question Decomposition Tree for Explainable Question Answeringcited by 11
  33. 2024KnowLA: Enhancing Parameter-efficient Finetuning with Knowledgeable Adaptationcited by 10
  34. 2024AtomR: Atomic Operator-Empowered Large Language Models for Heterogeneous Knowledge Reasoningcited by 10
  35. 2024Evidence-Focused Fact Summarization for Knowledge-Augmented Zero-Shot Question Answeringcited by 9
  36. 2024Temporal Knowledge Graph Question Answering: A Surveycited by 9
  37. 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
  38. 2022Nebula Graph: An open source distributed graph databasecited by 8

50 most cited of 64 All 64 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 8; 2026: 23.

31 papers.

Sort:

By area:

  1. 2026GAM: Hierarchical Graph-based Agentic Memory for LLM Agentscited by 19
  2. 2025Beyond Chunks and Graphs: Retrieval-Augmented Generation through Triplet-Driven Thinkingcited by 6
  3. 2025Knowing What's Missing: Assessing Information Sufficiency in Question Answeringcited by 3
  4. 2025SPARQL-LLM: Real-Time SPARQL Query Generation from Natural Language Questionscited by 3
  5. 2026Cost-Efficient RAG for Entity Matching with LLMs: A Blocking-based Explorationcited by 3
  6. 2026Fanar-Sadiq: A Multi-Agent Architecture for Grounded Islamic QAcited by 3
  7. 2026Knowledge Graph Representations for LLM-Based Policy Compliance Reasoningcited by 2
  8. 2026FedV-KGQA: Multi-Hop Question Answering over Vertically Partitioned Knowledge Graphscited by 2
  9. 2025Multi-dimensional Data Analysis and Applications Basing on LLM Agents and Knowledge Graph Interactionscited by 1
  10. 2025A systematic review of relation extraction task since the emergence of Transformerscited by 1
  11. 2025Focused Chain-of-Thought: Efficient LLM Reasoning via Structured Input Informationcited by 1
  12. 2025GOSU: Retrieval-Augmented Generation with Global-Level Optimized Semantic Unit-Centric Frameworkcited by 0
19 more
  1. 2025SLogic: Subgraph-Informed Logical Rule Learning for Knowledge Graph Completioncited by 0
  2. 2026Diagnosing Retrieval Bias Under Multiple In-Context Knowledge Updates in Large Language Modelscited by 0
  3. 2026BubbleRAG: Evidence-Driven Retrieval-Augmented Generation for Black-Box Knowledge Graphscited by 0
  4. 2026DepthCharge: A Domain-Agnostic Framework for Measuring Depth-Dependent Knowledge in Large Language Modelscited by 0
  5. 2026TRACE: An Experiential Framework for Coherent Multi-hop Knowledge Graph Question Answeringcited by 0
  6. 2026GS-Quant: Granular Semantic and Generative Structural Quantization for Knowledge Graph Completioncited by 0
  7. 2026KG-Guard: Graph-Based Hallucination Detection for Knowledge Base Question Answeringcited by 0
  8. 2026Improving Answer Extraction in Context-based Question Answering Systems Using LLMscited by 0
  9. 2026LLMs+Graphs: Toward Graph-Native, Synergistic AI Systemscited by 0
  10. 2026Measuring Semantic Progress in Multi-turn Dialogue via Information Gaincited by 0
  11. 2026Overcoming the Impedance Mismatch: A Theoretical Roadmap for Fusing Foundation Models and Knowledge Graphscited by 0
  12. 2026Efficient Retrieval-Augmented Generation via Token Co-occurrence Graphscited by 0
  13. 2026Constrained Entity Selection under Partial Knowledge for LLM-Based Knowledge Graph QAcited by 0
  14. 2026Pattern Over-Generalization of Knowledge Graph Embeddingcited by 0
  15. 2026What Drives Recovery in Agentic Text-to-Cypher? LAST-CQ: An LLM Agent Self-Refinement Frameworkcited by 0
  16. 2026FedV-KGQA in Practice: Design Lessons and an Interactive Prototypecited by 0
  17. 2026Cost Characterization of Vertically Partitioned Federated Knowledge Graphscited by 0
  18. 2026Symbolic Separation: Grounding Deep Agents in Knowledge Graphs for Trustworthy Operational Data Analyticscited by 0
  19. 2026Which Buildings Are Artificial Intelligence-Ready? A Measurement-Based Assessment Framework for AI Question Answering and Actuationcited by 0