CoChat
Sign Up
Cited by 27Topic ModelingAdvanced Graph Neural NetworksSemantic Web and Ontologies

The DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.

Debate on Graph: A Flexible and Reliable Reasoning Framework for Large Language Models

Open access
Ma, Jie, Gao, Zhitao, Chai, Qi, Sun, Wangchun, Wang, Pinghui, Pei, Hongbin, Tao, Jing, Song, Lingyun, Liu, Jun, Zhang, Chen, Cui, Lizhen·2025·Proceedings of the AAAI Conference on Artificial Intelligence
DOI 10.1609/aaai.v39i23.34658
Open this paper in CoChat — free accountOpen PDF

Abstract

Large Language Models (LLMs) may suffer from hallucinations in real-world applications due to the lack of relevant knowledge. In contrast, knowledge graphs encompass extensive, multi-relational structures that store a vast array of symbolic facts. Consequently, integrating LLMs with knowledge graphs has been extensively explored, with Knowledge Graph Question Answering (KGQA) serving as a critical touchstone for the integration. This task requires LLMs to answer natural language questions by retrieving relevant triples from knowledge graphs. However, existing methods face two significant challenges: *excessively long reasoning paths distracting from the answer generation*, and *false-positive relations hindering the path refinement*. In this paper, we propose an iterative interactive KGQA framework that leverages the interactive learning capabilities of LLMs to perform reasoning and Debating over Graphs (DoG). Specifically, DoG employs a subgraph-focusing mechanism, allowing LLMs to perform answer trying after each reasoning step, thereby mitigating the impact of lengthy reasoning paths. On the other hand, DoG utilizes a multi-role debate team to gradually simplify complex questions, reducing the influence of false-positive relations. This debate mechanism ensures the reliability of the reasoning process. Experimental results on five public datasets demonstrate the effectiveness and superiority of our architecture. Notably, DoG outperforms the state-of-the-art method ToG by 23.7% and 9.1% in accuracy on WebQuestions and GrailQA, respectively. Furthermore, the integration experiments with various LLMs on the mentioned datasets highlight the flexibility of DoG.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1609/aaai.v39i23.34658

Cites

3 of 3 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 3 references

Research works printed but not linked: 58

  1. Achiam, J.; Adler, S.; Agarwal, S.; Ahmad, L.; Akkaya, I.; Aleman, F. L.; Almeida, D.; Altenschmidt, J.; Altman, S.; Anadkat, S.; et al. 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774. · arXiv
  2. Baek, J.; Aji, A.; and Saffari, A. 2023. Knowledge- Augmented Language Model Prompting for Zero-Shot Knowledge Graph Question Answering. In ACL.
  3. Bai, J.; Liu, X.; Wang, W.; Luo, C.; and Song, Y. 2023. Com- plex query answering on eventuality knowledge graph with implicit logical constraints. In NeurIPS, 30534-30553.
  4. Berant, J.; Chou, A.; Frostig, R.; and Liang, P. 2013. Se- mantic parsing on freebase from question-answer pairs. In EMNLP, 1533-1544.
  5. Bollacker, K. D.; Evans, C.; Paritosh, P. K.; Sturge, T.; and Taylor, J. 2008. Freebase: a collaboratively created graph database for structuring human knowledge. In SIGMOD.
  6. Chan, C.-M.; Chen, W.; Su, Y.; Yu, J.; Xue, W.; Zhang, S.; Fu, J.; and Liu, Z. 2023. ChatEval: Towards Better LLM- based Evaluators through Multi-Agent Debate. In ICLR.
  7. Cui, Y.; Wang, Y.; Sun, Z.; Liu, W.; Jiang, Y.; Han, K.; and Hu, W. 2023. Lifelong embedding learning and transfer for growing knowledge graphs. In AAAI, 4217-4224.
  8. Dong, Q.; Li, L.; Dai, D.; Zheng, C.; Wu, Z.; Chang, B.; Sun, X.; Xu, J.; and Sui, Z. 2022. A survey on in-context learning. arXiv preprint arXiv:2301.00234. · arXiv
  9. Du, Y.; Li, S.; Torralba, A.; Tenenbaum, J. B.; and Mor- datch, I. 2023. Improving factuality and reasoning in lan- guage models through multiagent debate. arXiv preprint arXiv:2305.14325. · arXiv
  10. Gu, Y.; Deng, X.; and Su, Y. 2023. Don't Generate, Dis- criminate: A Proposal for Grounding Language Models to Real-World Environments. In ACL, 4928-4949.
  11. Guan, X.; Liu, Y.; Lin, H.; Lu, Y.; He, B.; Han, X.; and Sun, L. 2024. Mitigating large language model hallucinations via autonomous knowledge graph-based retrofitting. In AAAI, 18126-18134.
  12. Gunjal, A.; Yin, J.; and Bas, E. 2024. Detecting and prevent- ing hallucinations in large vision language models. In AAAI, 18135-18143.
  13. Guo, T.; Yang, Q.; Wang, C.; Liu, Y.; Li, P.; Tang, J.; Li, D.; and Wen, Y. 2023a. KnowledgeNavigator: Leveraging Large Language Models for Enhanced Reasoning over Knowledge Graph. arXiv preprint arXiv:2312.15880. · arXiv
  14. Guo, T.; Yang, Q.; Wang, C.; Liu, Y.; Li, P.; Tang, J.; Li, D.; and Wen, Y. 2023b. KnowledgeNavigator: Leverag- ing Large Language Models for Enhanced Reasoning over Knowledge Graph. arXiv preprint arXiv:2312.15880. · arXiv
  15. He, G.; Lan, Y.; Jiang, J.; Zhao, W. X.; and Wen, J.-R. 2021. Improving multi-hop knowledge base question answering by learning intermediate supervision signals. In WSDM, 553- 561.
  16. Hu, N.; Chen, J.; Wu, Y.; Qi, G.; Bi, S.; Wu, T.; and Pan, J. Z. 2024. Benchmarking Large Language Models in Complex Question Answering Attribution using Knowledge Graphs. CoRR, abs/2401.14640. · arXiv
  17. Ji, S.; Pan, S.; Cambria, E.; Marttinen, P.; and Yu, P. S. 2022. A Survey on Knowledge Graphs: Representation, Acquisi- tion, and Applications. IEEE TNNLS, 33(2): 494-514.
  18. Jiang, J.; Zhou, K.; Ye, K.; Zhao, X.; Wen, J.-R.; et al. 2023a. StructGPT: A General Framework for Large Lan- guage Model to Reason over Structured Data. In EMNLP.
  19. Jiang, J.; Zhou, K.; Zhao, W. X.; Song, Y.; Zhu, C.; Zhu, H.; and Wen, J.-R. 2024. KG-Agent: An Efficient Autonomous Agent Framework for Complex Reasoning over Knowledge Graph. arXiv preprint arXiv:2402.11163. · arXiv
  20. Jiang, J.; Zhou, K.; Zhao, X.; and Wen, J. 2023b. UniKGQA: Unified Retrieval and Reasoning for Solving Multi-hop Question Answering Over Knowledge Graph. In ICLR.
  21. Kim, J.; Kwon, Y.; Jo, Y.; and Choi, E. 2023. KG-GPT: A General Framework for Reasoning on Knowledge Graphs Using Large Language Models. In EMNLP.
  22. Kirk, J. R.; Wray, R. E.; Lindes, P.; and Laird, J. E. 2024. Im- proving Knowledge Extraction from LLMs for Task Learn- ing through Agent Analysis. In AAAI, 18390-18398.
  23. Kong, A.; Zhao, S.; Chen, H.; Li, Q.; Qin, Y.; Sun, R.; and Zhou, X. 2023. Better zero-shot reasoning with role-play prompting. arXiv preprint arXiv:2308.07702. · arXiv
  24. Li, G.; Hammoud, H.; Itani, H.; Khizbullin, D.; and Ghanem, B. 2023a. CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society. In NeurIPS, 51991-52008.
  25. Li, T.; Ma, X.; Zhuang, A.; Gu, Y.; Su, Y.; and Chen, W. 2023b. Few-shot In-context Learning on Knowledge Base Question Answering. In ACL, 6966-6980.
  26. Li, Z.; Fan, S.; Gu, Y.; Li, X.; Duan, Z.; Dong, B.; Liu, N.; and Wang, J. 2024. Flexkbqa: A flexible llm-powered frame- work for few-shot knowledge base question answering. In AAAI, 18608-18616.
  27. Lin, Q.; Liu, J.; Mao, R.; Xu, F.; and Cambria, E. 2023. TECHS: Temporal logical graph networks for explainable extrapolation reasoning. In ACL, 1281-1293.
  28. Liu, H.; Xue, W.; Chen, Y.; Chen, D.; Zhao, X.; Wang, K.; Hou, L.; Li, R.; and Peng, W. 2024. A survey on hallu- cination in large vision-language models. arXiv preprint arXiv:2402.00253. · arXiv
  29. Liu, X.; Yu, H.; Zhang, H.; Xu, Y.; Lei, X.; Lai, H.; Gu, Y.; Ding, H.; Men, K.; Yang, K.; et al. 2023. AgentBench: Evaluating LLMs as Agents. In ICLR.
  30. Luo, L.; Li, Y.-F.; Haf, R.; and Pan, S. 2023. Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning. In ICLR.
  31. Ma, J.; Wang, P.; Wang, Z.; Kong, D.; Hu, M.; Han, T.; and Liu, J. 2023. Adaptive loose optimization for robust question answering. arXiv preprint arXiv:2305.03971. · arXiv
  32. Miller, A.; Fisch, A.; Dodge, J.; Karimi, A.-H.; Bordes, A.; and Weston, J. 2016. Key-Value Memory Networks for Di- rectly Reading Documents. In EMNLP, 1400-1409.
  33. Nie, Z.; Zhang, R.; Wang, Z.; and Liu, X. 2024. Code-style in-context learning for knowledge-based question answer- ing. In AAAI, 18833-18841.
  34. Qian, C.; Cong, X.; Yang, C.; Chen, W.; Su, Y.; Xu, J.; Liu, Z.; and Sun, M. 2023. Communicative agents for software development. arXiv preprint arXiv:2307.07924. · arXiv
  35. Quintero-Narvaez, C. E.; and Monroy, R. 2024. Integrating Knowledge Graph Data with Large Language Models for Explainable Inference. In WSDM, 1198-1199.
  36. Saxena, A.; Tripathi, A.; and Talukdar, P. 2020. Improving multi-hop question answering over knowledge graphs using knowledge base embeddings. In ACL, 4498-4507.
  37. Schumann, R.; Zhu, W.; Feng, W.; Fu, T.-J.; Riezler, S.; and Wang, W. Y. 2024. Velma: Verbalization embodiment of llm agents for vision and language navigation in street view. In AAAI, 18924-18933.
  38. Shen, C.; Xie, G.; Zhang, X.; and Xu, J. 2024. On the Decision-Making Abilities in Role-Playing using Large Language Models. arXiv preprint arXiv:2402.18807. · arXiv
  39. Shi, J.; Cao, S.; Hou, L.; Li, J.; and Zhang, H. 2021. Trans- ferNet: An Effective and Transparent Framework for Multi- hop Question Answering over Relation Graph. In EMNLP, 4149-4158.
  40. Shi, X.; Zhu, Z.; Zhang, Z.; and Li, C. 2023. Hallucination mitigation in natural language generation from large-scale open-domain knowledge graphs. In EMNLP, 12506-12521.
  41. Shu, Y.; Yu, Z.; Li, Y.; Karlsson, B.; Ma, T.; Qu, Y.; and Lin, C.-Y. 2022. TIARA: Multi-grained Retrieval for Ro- bust Question Answering over Large Knowledge Base. In EMNLP, 8108-8121.
  42. Sun, H.; Bedrax-Weiss, T.; and Cohen, W. W. 2019. Pullnet: Open domain question answering with iterative retrieval on knowledge bases and text. arXiv preprint arXiv:1904.09537. · arXiv
  43. Sun, H.; Dhingra, B.; Zaheer, M.; Mazaitis, K.; Salakhutdi- nov, R.; and Cohen, W. 2018. Open Domain Question An- swering Using Early Fusion of Knowledge Bases and Text. In EMNLP, 4231-4242.
  44. Sun, J.; Xu, C.; Tang, L.; Wang, S.; Lin, C.; Gong, Y.; Ni, L.; Shum, H.-Y.; and Guo, J. 2024. Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph. In ICLR.
  45. Talmor, A.; and Berant, J. 2018. The Web as a Knowledge- Base for Answering Complex Questions. In NAACL, 641- 651.
  46. Toroghi, A.; Guo, W.; Pour, M. M. A.; and Sanner, S. 2024. Right for Right Reasons: Large Language Models for Verifi- able Commonsense Knowledge Graph Question Answering. arXiv preprint arXiv:2403.01390. · arXiv
  47. Wang, S.; Scells, H.; Koopman, B.; and Zuccon, G. 2023. Can ChatGPT write a good boolean query for systematic re- view literature search? In SIGIR, 1426-1436.
  48. Wang, Y.; Lipka, N.; Rossi, R. A.; Siu, A.; Zhang, R.; and Derr, T. 2024. Knowledge graph prompting for multi- document question answering. In AAAI, 19206-19214.
  49. Wei, J.; Wang, X.; Schuurmans, D.; Bosma, M.; Xia, F.; Chi, E.; Le, Q. V.; Zhou, D.; et al. 2022. Chain-of-thought prompting elicits reasoning in large language models. In NeurIPS, 24824-24837.
  50. Wei, Y.; Huang, Q.; Zhang, Y.; and Kwok, J. 2023. KICGPT: Large Language Model with Knowledge in Context for Knowledge Graph Completion. In Findings of EMNLP, 8667-8683.
  51. Xiong, G.; Bao, J.; and Zhao, W. 2024. Interactive- KBQA: Multi-Turn Interactions for Knowledge Base Ques- tion Answering with Large Language Models. CoRR, abs/2402.15131. · arXiv
  52. Yang, D.; Yang, K.; Wang, Y.; Liu, J.; Xu, Z.; Yin, R.; Zhai, P.; and Zhang, L. 2023. How2comm: communication- efficient and collaboration-pragmatic multi-agent percep- tion. In NeurIPS, 25151-25164.
  53. Ye, X.; Yavuz, S.; Hashimoto, K.; Zhou, Y.; and Xiong, C. 2022. RNG-KBQA: Generation Augmented Iterative Rank- ing for Knowledge Base Question Answering. In ACL, 6032-6043.
  54. Yih, W.-t.; Richardson, M.; Meek, C.; Chang, M.-W.; and Suh, J. 2016. The value of semantic parse labeling for knowledge base question answering. In ACL, 201-206.
  55. Zhang, J.; Xu, X.; and Deng, S. 2023. Exploring collabora- tion mechanisms for llm agents: A social psychology view. arXiv preprint arXiv:2310.02124. · arXiv
  56. Zhang, Y.; Dai, H.; Kozareva, Z.; Smola, A.; and Song, L. 2018. Variational reasoning for question answering with knowledge graph. In AAAI.
  57. Zhang, Y.; Li, Y.; Cui, L.; Cai, D.; Liu, L.; Fu, T.; Huang, X.; Zhao, E.; Zhang, Y.; Chen, Y.; et al. 2023. Siren's song in the AI ocean: a survey on hallucination in large language models. arXiv preprint arXiv:2309.01219. · arXiv
  58. Zhao, A.; Huang, D.; Xu, Q.; Lin, M.; Liu, Y.-J.; and Huang, G. 2024. Expel: Llm agents are experiential learners. In AAAI, 19632-19642.

Cited by

Sorted by citations

See all 27

Metadata

Authors
Ma, J., Gao, Z., Chai, Q., Sun, W., Wang, P., Pei, H., Tao, J., Song, L., Liu, J., Zhang, C., & Cui, L.
Affiliations
  • Xi'an Jiaotong University (CN)
  • The Hong Kong University of Science and Technology (Guangzhou) (CN)
  • Northwestern Polytechnical University (CN)
  • Shandong University (CN)
ORCID
Venue
Proceedings of the AAAI Conference on Artificial Intelligence
Publisher
Association for the Advancement of Artificial Intelligence (AAAI)
Published
2025-04-11
Volume
39
Issue
23
Pages
24768-24776
ISSN
  • 2159-5399 (ISSN-L)
  • 2374-3468
DOI
10.1609/aaai.v39i23.34658
OpenAlex
W4409348126
Cited by
27
References
3
Citations by year
2026: 13 · 2025: 14
FWCI
25.60
Type
conference paper
Language
en
Open access
Locations
  • Proceedings of the AAAI Conference on Artificial Intelligence (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University)
Funders
  • National Natural Science Foundation of China (62306229, U22B2019, 62437002, 62293553, 62372362)
  • China Postdoctoral Science Foundation
  • Shaanxi Science and Technology Association
  • National Key Research and Development Program of China (2022YFC3303600)
  • Key Research and Development Projects of Shaanxi Province
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
  • Physical Sciences › Computer Science › Artificial Intelligence › Advanced Graph Neural Networks
  • Physical Sciences › Computer Science › Artificial Intelligence › Semantic Web and Ontologies
Keywords
knowledge graph question answering, large language models, hallucination mitigation

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Debate on Graph: A Flexible and Reliable Reasoning Framework for Large Language Models. https://app.cochat.ai/papers/10.1609/aaai.v39i23.34658
The paper
Ma, J., Gao, Z., Chai, Q., Sun, W., Wang, P., Pei, H., Tao, J., Song, L., Liu, J., Zhang, C., & Cui, L. (2025). Debate on Graph: A Flexible and Reliable Reasoning Framework for Large Language Models. Proceedings of the AAAI Conference on Artificial Intelligence. https://doi.org/10.1609/aaai.v39i23.34658