mlsanityData to 7 Oct 2026

UniKGQA: Unified Retrieval and Reasoning for Solving Multi-hop Question Answering Over Knowledge Graph

arXiv 2212.00959 ↗First posted 2 Dec 2022cs.CLcited by 100

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

Abstract (arXiv)

Multi-hop Question Answering over Knowledge Graph~(KGQA) aims to find the answer entities that are multiple hops away from the topic entities mentioned in a natural language question on a large-scale Knowledge Graph (KG). To cope with the vast search space, existing work usually adopts a two-stage approach: it first retrieves a relatively small subgraph related to the question and then performs the reasoning on the subgraph to find the answer entities accurately. Although these two stages are highly related, previous work employs very different technical solutions for developing the retrieval and reasoning models, neglecting their relatedness in task essence. In this paper, we propose UniKGQA, a novel approach for multi-hop KGQA task, by unifying retrieval and reasoning in both model architecture and parameter learning. For model architecture, UniKGQA consists of a semantic matching module based on a pre-trained language model~(PLM) for question-relation semantic matching, and a matching information propagation module to propagate the matching information along the directed edges on KGs. For parameter learning, we design a shared pre-training task based on question-relation matching for both retrieval and reasoning models, and then propose retrieval- and reasoning-oriented fine-tuning strategies. Compared with previous studies, our approach is more unified, tightly relating the retrieval and reasoning stages. Extensive experiments on three benchmark datasets have demonstrated the effectiveness of our method on the multi-hop KGQA task. Our codes and data are publicly available at~urlhttps://github.com/RUCAIBox/UniKGQA.

Key facts. Cited by 100 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 21 of its 31 references that are in the map. First posted on arXiv 2 Dec 2022.

Builds on

21 of 31 references.

References · 21

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  3. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  4. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  5. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  6. 2017Reading Wikipedia to Answer Open-Domain Questionscited by 777
  7. 2018The Web as a Knowledge-base for Answering Complex Questionscited by 409
  8. 2016Key-Value Memory Networks for Directly Reading Documentscited by 223
  9. 2019PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Textcited by 182
  10. 2017Variational Reasoning for Question Answering with Knowledge Graphcited by 170
  11. 2018Open Domain Question Answering Using Early Fusion of Knowledge Bases and Textcited by 167
  12. 2019Learning by Abstraction: The Neural State Machinecited by 113
9 more
  1. 2021Case-based Reasoning for Natural Language Queries over Knowledge Basescited by 107
  2. 2021Improving Multi-hop Knowledge Base Question Answering by Learning Intermediate Supervision Signalscited by 100
  3. 2022Subgraph Retrieval Enhanced Model for Multi-hop Knowledge Base Question Answeringcited by 93
  4. 2021A Survey on Complex Knowledge Base Question Answering: Methods, Challenges and Solutionscited by 77
  5. 2021End-to-End Training of Neural Retrievers for Open-Domain Question Answeringcited by 75
  6. 2021TransferNet: An Effective and Transparent Framework for Multi-hop Question Answering over Relation Graphcited by 60
  7. 2019Bidirectional Attentive Memory Networks for Question Answering over Knowledge Basescited by 30
  8. 2022SimANS: Simple Ambiguous Negatives Sampling for Dense Text Retrievalcited by 21
  9. 2022Great Truths are Always Simple: A Rather Simple Knowledge Encoder for Enhancing the Commonsense Reasoning Capacity of Pre-Trained Modelscited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 11; 2024: 27; 2025: 43; 2026: 19.

100 papers.

Sort:

By area:

  1. 2023Unifying Large Language Models and Knowledge Graphs: A Roadmapcited by 663
  2. 2023StructGPT: A General Framework for Large Language Model to Reason over Structured Datacited by 339
  3. 2023Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoningcited by 326
  4. 2024Graph Retrieval-Augmented Generation: A Surveycited by 320
  5. 2024GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoningcited by 128
  6. 2024KG-Agent: An Efficient Autonomous Agent Framework for Complex Reasoning over Knowledge Graphcited by 90
  7. 2024Simple Is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generationcited by 78
  8. 2024Plan-on-Graph: Self-Correcting Adaptive Planning of Large Language Model on Knowledge Graphscited by 77
  9. 2023KnowledGPT: Enhancing Large Language Models with Retrieval and Storage Access on Knowledge Basescited by 52
  10. 2024Graph-constrained Reasoning: Faithful Reasoning on Knowledge Graphs with Large Language Modelscited by 47
  11. 2023ChatKBQA: A Generate-then-Retrieve Framework for Knowledge Base Question Answering with Fine-tuned Large Language Modelscited by 44
  12. 2024FiDeLiS: Faithful Reasoning in Large Language Model for Knowledge Graph Question Answeringcited by 38
38 more
  1. 2023KG-GPT: A General Framework for Reasoning on Knowledge Graphs Using Large Language Modelscited by 32
  2. 2023Knowledgeable Preference Alignment for LLMs in Domain-specific Question Answeringcited by 28
  3. 2024Knowledge Graph-Enhanced Large Language Models via Path Selectioncited by 28
  4. 2024Interactive-KBQA: Multi-Turn Interactions for Knowledge Base Question Answering with Large Language Modelscited by 25
  5. 2024Harnessing Large Language Models for Knowledge Graph Question Answering via Adaptive Multi-Aspect Retrieval-Augmentationcited by 24
  6. 2023ReasoningLM: Enabling Structural Subgraph Reasoning in Pre-trained Language Models for Question Answering over Knowledge Graphcited by 23
  7. 2023KnowledgeNavigator: Leveraging Large Language Models for Enhanced Reasoning over Knowledge Graphcited by 22
  8. 2023Memory Injections: Correcting Multi-Hop Reasoning Failures during Inference in Transformer-Based Language Modelscited by 21
  9. 2024Two-stage Generative Question Answering on Temporal Knowledge Graph Using Large Language Modelscited by 18
  10. 2025Graph-based Approaches and Functionalities in Retrieval-Augmented Generation: A Comprehensive Surveycited by 18
  11. 2024Enhancing Complex Question Answering over Knowledge Graphs through Evidence Pattern Retrievalcited by 16
  12. 2024TRACE the Evidence: Constructing Knowledge-Grounded Reasoning Chains for Retrieval-Augmented Generationcited by 16
  13. 2025Ontology-Guided Reverse Thinking Makes Large Language Models Stronger on Knowledge Graph Question Answeringcited by 15
  14. 2025LLM/Agent-as-Data-Analyst: A Surveycited by 15
  15. 2024Question-guided Knowledge Graph Re-scoring and Injection for Knowledge Graph Question Answeringcited by 13
  16. 2024CypherBench: Towards Precise Retrieval over Full-scale Modern Knowledge Graphs in the LLM Eracited by 13
  17. 2025VistaWise: Building Cost-Effective Agent with Cross-Modal Knowledge Graph for Minecraftcited by 13
  18. 2024TrustUQA: A Trustful Framework for Unified Structured Data Question Answeringcited by 12
  19. 2025Memory-augmented Query Reconstruction for LLM-based Knowledge Graph Reasoningcited by 10
  20. 2025BYOKG-RAG: Multi-Strategy Graph Retrieval for Knowledge Graph Question Answeringcited by 10
  21. 2025Align-GRAG: Anchor and Rationale Guided Dual Alignment for Graph Retrieval-Augmented Generationcited by 9
  22. 2025Reliable Reasoning Path: Distilling Effective Guidance for LLM Reasoning with Knowledge Graphscited by 9
  23. 2025FRAG: A Flexible Modular Framework for Retrieval-Augmented Generation based on Knowledge Graphscited by 8
  24. 2025Beyond Seen Data: Improving KBQA Generalization Through Schema-Guided Logical Form Generationcited by 8
  25. 2025A Survey on Retrieval And Structuring Augmented Generation with Large Language Modelscited by 8
  26. 2026Retrieval--Reasoning Processes for Multi-hop Question Answering: A Four-Axis Design Framework and Empirical Trendscited by 8
  27. 2024LEGO-GraphRAG: Modularizing Graph-based Retrieval-Augmented Generation for Design Space Explorationcited by 7
  28. 2024KARPA: A Training-free Method of Adapting Knowledge Graph as References for Large Language Model's Reasoning Path Aggregationcited by 7
  29. 2025EPERM: An Evidence Path Enhanced Reasoning Model for Knowledge Graph Question and Answeringcited by 7
  30. 2025Reason-Align-Respond: Aligning LLM Reasoning with Knowledge Graphs for KGQAcited by 7
  31. 2024Multi-hop Question Answering over Knowledge Graphs using Large Language Modelscited by 6
  32. 2024Knowledge Graph Tuning: Real-time Large Language Model Personalization based on Human Feedbackcited by 6
  33. 2024SimGRAG: Leveraging Similar Subgraphs for Knowledge Graphs Driven Retrieval-Augmented Generationcited by 6
  34. 2025Loki's Dance of Illusions: A Comprehensive Survey of Hallucination in Large Language Modelscited by 6
  35. 2025DAMR: Efficient and Adaptive Context-Aware Knowledge Graph Question Answering with LLM-Guided MCTScited by 6
  36. 2026Membox: Weaving Topic Continuity into Long-Range Memory for LLM Agentscited by 6
  37. 2024How Proficient Are Large Language Models in Formal Languages? An In-Depth Insight for Knowledge Base Question Answeringcited by 5
  38. 2024Knowledge graph enhanced retrieval-augmented generation for failure mode and effects analysiscited by 5

50 most cited of 100 All 100 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025StepChain GraphRAG: Reasoning Over Knowledge Graphs for Multi-Hop Question Answering
  2. 2025Efficient Multi-Hop Question Answering over Knowledge Graphs via LLM Planning and Embedding-Guided Search
  3. 2026MARS: Multi-hop Adaptive Retrieval and SPARQL Generation for KGQA
  4. 2025KG-o1: Enhancing Multi-hop Question Answering in Large Language Models via Knowledge Graph Integration
  5. 2026Theseus in the Graph: Towards Traceable Multi-Hop Graph Navigation
  6. 2025iQUEST: An Iterative Question-Guided Framework for Knowledge Base Question Answering
  7. 2022Exploiting Hybrid Semantics of Relation Paths for Multi-hop Question Answering Over Knowledge Graphs
  8. 2024MINTQA: A Multi-Hop Question Answering Benchmark for Evaluating LLMs on New and Tail Knowledge