Reliability-Aware Slot Selection for Dialogue State Tracking in Noisy Multi-Turn Conversations
DOI:
https://doi.org/10.66238/41h0tr06Keywords:
Dialogue State Tracking, Slot Selectio, Noise Robustness, Conversational AgentsAbstract
Dialogue State Tracking represents a foundational component within task-oriented dialogue systems, responsible for extracting and maintaining user goals across multiple conversation turns in the form of slot-value pairs. However, in real-world scenarios, these systems frequently encounter noisy multi-turn conversations characterized by automatic speech recognition errors, user hesitations, ambiguous coreferences, and sudden conversational domain shifts. Traditional dialogue state tracking models generally assume clean input texts and fail to adequately filter out erroneous slot candidates, leading to severe error propagation as the dialogue progresses. To address this persistent challenge, this paper proposes a novel Reliability-Aware Slot Selection framework designed to explicitly evaluate the confidence and stability of slot candidates before incorporating them into the dialogue state. By conceptualizing slot selection as a dynamic reliability estimation problem, the proposed framework leverages multi-head temporal attention mechanisms to quantify the historical consistency of extracted values. We introduce a specialized reliability metric that dynamically penalizes highly volatile or linguistically ambiguous slot predictions. Extensive empirical evaluations conducted on widely recognized benchmark datasets demonstrate that our proposed approach significantly outperforms existing baseline models in terms of Joint Goal Accuracy, particularly under simulated high-noise conditions. The findings highlight the critical importance of embedding reliability metrics directly into the state updating mechanism, paving the way for more robust and resilient conversational agents in unpredictable real-world environments.
References
1. Xu, X., Tu, W., & Yang, Y. (2025). Efficient audio–visual information fusion using encoding pace synchronization for Audio–Visual Speech Separation. Information Fusion, 115, 102749.
2. Xu, X., Tu, W., & Yang, Y. (2024). Adaptive selection of local and non-local attention mechanisms for speech enhancement.Neural Networks,174, 106236.
3. Pei, Zhengqi, Qingming Huang, and Shuhui Wang. "When LLMs develop languages: Symbolic communication for efficient multi-agent reasoning." arXiv preprint arXiv:2606.29354 (2026).
4. Yu, H., Zhang, J., Chen, C., Xiang, T., Fang, Y., Niebles, J. C., & Adeli, E. (2026, March). Socialgen: Modeling multi-human social interaction with language models. In 2026 International Conference on 3D Vision (3DV) (pp. 1-17). IEEE.
5. Ning, X., Tieu, K., Fu, D., Wei, T., Li, Z., Bei, Y.,... & He, J. (2026). Code as agent harness. arXiv preprint arXiv:2605.18747.
6. Zhang, Y., Zhang, Y., Zhao, M., Feng, S., & Cheung, Y. M. (2026). How to Ask the AI: A User Perspective Survey for Large Language Model Prompting.IEEE Transactions on Artificial Intelligence.
7. Li, Y., Bai, X., Liu, S., & Zhang, L. (2026). RepBench: Compiling benchmarks into capability representations for large language models. arXiv. https://arxiv.org/abs/2607.28008
8. 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.
9. Zhu, R., Ma, Z., Wu, J., Gao, J., Wang, J., Lin, D., & He, C. (2025, April). Utilize the flow before stepping into the same river twice: Certainty represented knowledge flow for refusal-aware instruction tuning. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 39, No. 24, pp. 26157-26165).
10. Han, C., Tan, J., Yu, B., Zheng, W., & Tang, X. (2026). Conformity Dynamics in LLM Multi-Agent Systems: The Roles of Topology and Self-Social Weighting.arXiv preprint arXiv:2601.05606.
11. 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.
12. Sang, Y. (2025, August). Robustness of fine-tuned llms under noisy retrieval inputs. In 2025 6th International Conference on Artificial Intelligence and Electromechanical Automation (AIEA) (pp. 417-420). IEEE.
13. 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.
14. Tang, J., Yuan, X., Liu, J., Yu, J., Dong, X., Chen, L., ... & Yin, J. (2026). SAKE: Self-aware Knowledge Exploitation-Exploration for Grounded Multimodal Named Entity Recognition. arXiv preprint arXiv:2604.20146.
15. Yao, Y., Zhang, J., Miao, P., Zhang, L., Chen, G., Shu, F., & Wong, K. K. (2025). Hybrid RIS-enhanced ISAC secure systems: Joint optimization in the presence of an extended target. IEEE Transactions on Communications.
16. Li, Y., Yang, Z., Huang, Y., Liu, X., & Qi, G. (2026, March). C³TG: Conflict-aware, Composite, and Collaborative Controlled Text Generation. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 40, No. 38, pp. 31834-31842).
17. Wei, W. D., Fang, H. B., Liu, Y. D., Shi, J. X., Kwok, J., & Li, Y. F. (2026). Activation Compression in LLMs: Theoretical Analysis and Efficient Algorithm. arXiv preprint arXiv:2605.01255.
18. Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.-A., Lacroix, T., et al. (2023). LLaMA: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971.
19. Yang Y, Yang X, Jiang Y, et al. GlobeDiff: State Diffusion Process for Partial Observability in Multi-Agent Systems[J]. arXiv preprint arXiv:2602.15776, 2026.
20. Guo, J., Shuang, K., Li, J., Wang, Z., & Liu, Y. (2022, May). Beyond the granularity: Multi-perspective dialogue collaborative selection for dialogue state tracking. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (pp. 2320-2332).
21. Mao, C., Shuang, K., Guo, J., Qian, B., Yang, Y., & Li, H. (2026). Cognition-aligned frequency filtering for sentence embeddings. Information Processing & Management, 63(2), 104415.
22. Liu, H., Lin, R., Kashyap, A., Cui, H., Henao, R., Fetahu, B., & Yin, B. (2026). Customer-Agent: Overcoming Context Limitations in Ultra-Long Shopping Trajectories via Tool-Augmented Agents and RLVR. arXiv preprint arXiv:2606.07995.
23. Wang, S. (2025, May). W-PCA based gradient-free proxy for efficient search of lightweight language models. In International Conference on Learning Representations (Vol. 2025, pp. 42419-42440).
24. Xu, X., Tu, W., & Yang, Y. (2023). CASE-Net: Integrating local and non-local attention operations for speech enhancement. Speech Communication, 148, 31-39.
25. Yao, Y., Xiao, W., Miao, P., Chen, G., Yang, H., Chae, C. B., & Wong, K. K. (2026). UAV-RHS-enabled full-duplex ISAC covert system: Robust beamforming and trajectory optimization. IEEE Transactions on Communications.
26. Li, X., Wang, P., Li, G., Ni, L., & Zhang, Y. (2023). Design of interface circuits and lightweight PUF for TMR sensors. IEEE Sensors Journal, 23(11), 11754-11761.
27. Yao, Y., Xiao, W., Miao, P., Chen, G., Yang, H., Chae, C. B., & Wong, K. K. (2025). UAV-relay-aided secure maritime networks coexisting with satellite networks: robust beamforming and trajectory optimization. IEEE Transactions on Wireless Communications.
28. 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).
29. Zhu, R., Jiang, Z., Wu, J., Ma, Z., Song, J., Bai, F., ... & He, C. (2025, April). Grait: Gradient-driven refusal-aware instruction tuning for effective hallucination mitigation. In Findings of the Association for Computational Linguistics: NAACL 2025 (pp. 4006-4021).
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Juan Castillo López, Valentina López (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
All articles published in the International Journal of Machine Learning and Engineering (IJMLE) are licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).
This license permits unrestricted use, distribution, reproduction, adaptation, and commercial use in any medium or format, provided the original author(s) and the source are properly credited.
Authors retain the copyright of their work while granting the journal the right of first publication.
To view a copy of this license, please visit:
https://creativecommons.org/licenses/by/4.0/
