Verifier-Mediated Debate for Controllable Question Synthesis over Knowledge Graphs
DOI:
https://doi.org/10.66238/smsrj.v4i2.71Keywords:
Knowledge Graphs, Question Synthesis, Multi-Agent Debate, Controllable GenerationAbstract
The rapid expansion of knowledge graphs has necessitated advanced interfaces capable of translating structured data into natural language queries, an area known as question synthesis. Traditional approaches to question synthesis over knowledge graphs often struggle with semantic fidelity, hallucination, and a lack of structural controllability, particularly as the complexity of the underlying subgraphs increases. This paper introduces a novel framework, Verifier-Mediated Debate, designed to address these challenges by employing a multi-agent debate mechanism strictly regulated by a deterministic verifier. By casting question generation as a discursive process between opposing generative agents, the proposed system iteratively refines syntactic coherence and structural alignment. A neutral verifying agent, grounded explicitly in the source knowledge graph schema, objectively evaluates proposed questions at each debate round, terminating the discourse once optimal semantic fidelity is achieved. Extensive theoretical analysis and empirical evaluations demonstrate that this framework significantly enhances the controllability and accuracy of synthesized questions compared to single-agent generative paradigms. The integration of a deterministic verifier curtails the introduction of spurious information, thereby resolving a critical bottleneck in large language model applications for structured data. This research advances the paradigm of neuro-symbolic integration and establishes a robust foundation for building trustworthy, automated question generation systems tailored for complex knowledge repositories.
References
1. Zhao, R., Tang, J., Zeng, W., Chen, Z., & Zhao, X. (2024, October). Zero-shot knowledge graph question generation via multi-agent llms and small models synthesis. In Proceedings of the 33rd ACM International Conference on Information and Knowledge Management (pp. 3341-3351).
2. Huang, Y., Thede, L., Mancini, M., Xu, W., & Akata, Z. (2025, September). Investigating structural pruning and recovery techniques for compressing multimodal large language models: An empirical study. In DAGM german conference on pattern recognition (pp. 320-336). Cham: Springer Nature Switzerland.
3. Yu, R., Wang, Y., Jiao, X., Zhang, Y., & Kwok, J. T. (2024). Direct alignment of language models via quality-aware self-refinement. arXiv preprint arXiv:2405.21040.
4. Sang, Y. (2025, July). Towards explainable rag: Interpreting the influence of retrieved passages on generation. In 2025 4th International Conference on Robotics, Artificial Intelligence and Intelligent Control (RAIIC) (pp. 397-400). IEEE.
5. Sang, Y. (2025, October). AutoCrit: A Meta-Reasoning Framework for Self-Critique and Iterative Error Correction in LLM Chains-of-Thought. In 2025 6th International Conference on Machine Learning and Computer Application (ICMLCA) (pp. 1177-1180). IEEE.
6. Tang, J., Wang, Z., Gong, Z., Yu, J., Zhu, X., & Yin, J. (2025, April). Multi-grained query-guided set prediction network for grounded multimodal named entity recognition. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 39, No. 24, pp. 25246-25254).
7. Tang, J., Yang, Y., Yu, J., Wang, Z. X., Liang, H., Yao, L., & Yin, J. (2025, November). Unco: Uncertainty-driven collaborative framework of large and small models for grounded multimodal ner. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (pp. 7644-7662).
8. Su, Yiyun, et al. "Agentic-SQL Taxonomy: A Survey of Autonomous and Interactive Text-to-SQL with LLMs." (2026).
9. Cao, Y., Jing, L., Wang, Y., Shi, D., Yu, C., & Xing, J. (2026, June). Dual-Pathway Diffusion for Hand Correction in Synthetic Portraits: Global Context Aware and Local Structure Refinement. In Proceedings of the 2026 International Conference on Multimedia Retrieval (pp. 1899-1907).
10. Qiu, Z., Lyu, H., Xiong, W., & Luo, J. (2025). Can llms simulate social media engagement? a study on action-guided response generation. arXiv preprint arXiv:2502.12073.
11. Yang, Y., Yang, X., Jiang, Y., Mu, N., Hu, H., Xie, R., ... & Xu, B. (2026). GlobeDiff: State Diffusion Process for Partial Observability in Multi-Agent Systems. arXiv preprint arXiv:2602.15776.
12. Li, X., He, H., Lu, G., Yue, P., Chen, J., Yang, Z., & Hon, C. (2025). TCM-DS: a large language model for intelligent traditional Chinese medicine edible herbal formulas recommendations. Chinese Medicine, 20(1), 191.
13. Reimers, N., & Gurevych, I. (2019). Sentence-BERT: Sentence embeddings using Siamese BERT-networks. In Proceedings of EMNLP-IJCNLP.
14. Vinyals, O., Fortunato, M., & Jaitly, N. (2015). Pointer networks. In Advances in Neural Information Processing Systems.
15. Yao, Y., Shu, F., Li, Z., Cheng, X., & Wu, L. (2023). Secure transmission scheme based on joint radar and communication in mobile vehicular networks. IEEE transactions on intelligent transportation systems, 24 (9), 10027-10037.
16. Li, Q., Ye, Q., Zhang, N., Zhang, W., & Hu, F. (2025). Digital-twin-enabled industrial IoT: Vision, framework, and future directions. IEEE Wireless Communications, 32(6), 173-181.
17. Wang, S., Zhang, X., Wang, P., & Li, X. (2026). Design of Magnetic Sensor Array-Based PUFs for IoT Security. IEEE Transactions on Instrumentation and Measurement, 75, 1-9.
18. Zhang, B., Wang, S., Jiang, Y., Sui, D., Tu, Z., & Chu, D. (2025, July). Ask and Retrieve Knowledge: Towards Proactive Asking with Imperfect Information in Medical Multi-turn Dialogues. In Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval (pp. 1055-1065).
19. Li, S. (2024). Machine Learning in Credit Risk Forecasting — — A Survey on Credit Risk Exposure. Accounting and Finance Research, 13(2), 107-107.
20. Pei, Z., Huang, Q., & Wang, S. (2026). When LLMs develop languages: Symbolic communication for efficient multi-agent reasoning. arXiv preprint arXiv:2606.29354.
21. Chen, L., Wang, J., Mortlock, T., Khargonekar, P., & Al Faruque, M. A. (2025, June). Hyperdimensional uncertainty quantification for multimodal uncertainty fusion in autonomous vehicles perception. In 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 22306-22316). IEEE.
22. Liao, Q., Chen, Y., He, S., Wang, R., Xu, W., & Chu, W. (2025). Explainable Artificial Intelligence for 5G Security and Privacy: Trust, Governance, and Resilience.
23. Kabra, Meha, et al. "Nonviral base editing of KCNJ13 mutation preserves vision in a model of inherited retinal channelopathy." The Journal of Clinical Investigation 133.19 (2023).
24. Li, Z., Dong, Y., Gao, C., Zhao, Y., Li, D., Hao, J., ... & Wang, Z. (2023, April). Breaking filter bubble: A reinforcement learning framework of controllable recommender system. In Proceedings of the ACM Web Conference 2023 (pp. 4041-4049).
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Lisa Weiß
This work is licensed under a Creative Commons Attribution 4.0 International License.
All articles in the Social and Management Sciences Research Journal are published under the Creative Commons Attribution 4.0 (CC BY 4.0) license. Users can share, copy, distribute, and adapt the work, including for commercial purposes, provided proper attribution is given to the authors and the journal.
