Refusal-Aware Instruction Tuning for Hallucination Mitigation near Uncertain Knowledge Boundaries
DOI:
https://doi.org/10.66525/ijictt111Keywords:
Instruction Tuning, Hallucination Mitigation, Knowledge Boundaries, Epistemic UncertaintyAbstract
The rapid deployment of large language models has exposed significant vulnerabilities in their reliability, particularly concerning their propensity to hallucinate when confronted with queries that exceed their internalized knowledge capacities. This paper investigates the critical challenge of mitigating hallucinations near uncertain knowledge boundaries through a novel paradigm termed refusal-aware instruction tuning. Conventional instruction tuning often inadvertently encourages models to generate responses even when uncertain, prioritizing fluency and helpfulness over factual accuracy. To counteract this phenomenon, we propose a systematic framework that integrates uncertainty quantification directly into the instruction tuning pipeline, teaching models to explicitly refuse to answer when a query falls outside their reliable knowledge distribution. By formalizing the concept of uncertain knowledge boundaries, we develop a specialized dataset curation strategy that identifies low-confidence regions and pairs them with appropriate refusal responses. Our methodology is subsequently evaluated through extensive empirical analysis, demonstrating that refusal-aware instruction tuning substantially reduces hallucination rates without compromising the utility of the model on well-known facts. The findings suggest that aligning models with their own epistemic limitations is a fundamental requirement for deploying trustworthy artificial intelligence systems in high-stakes domains.
Downloads
References
1. 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.
2. Xu, X., Tu, W., & Yang, Y. (2023, June). Selector-enhancer: learning dynamic selection of local and non-local attention operation for speech enhancement. In Proceedings of the AAAI conference on artificial intelligence (Vol. 37, No. 11, pp. 13853-13860).
3. Ou, J., Guo, J., Jiang, S., Wang, Z., Chen, Y., Xue, R., & Tian, W. (2025, June). Low-Rank Decomposition Assisted Quantization and Inference Compensation for Quality Large Language Model Inference. In 2025 International Joint Conference on Neural Networks (IJCNN) (pp. 1-9). IEEE.
4. Gao, Z., Qu, Y., & Han, Y. (2025). Cross-Lingual Sponsored Search via Dual-Encoder and Graph Neural Networks for Context-Aware Query Translation in Advertising Platforms. arXiv preprint arXiv:2510.22957.
5. Xu, X., Tu, W., Yang, Y., Li, J., Zhang, Y., & Chen, H. (2026). Contribution-aware dynamic multi-modal balance for audio-visual speech separation.IEEE Transactions on Multimedia.
6. 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).
7. Rafailov, R., Sharma, A., Mitchell, E., Manning, C. D., Ermon, S., & Finn, C. (2024). Direct preference optimization: Your language model is secretly a reward model. In Advances in Neural Information Processing Systems.
8. 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.
9. Zhang, K., Shuang, K., Yang, X., Yao, X., & Guo, J. (2023, July). What is overlap knowledge in event argument extraction? APE: A cross-datasets transfer learning model for EAE. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (pp. 393-409).
10. 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.
11. Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of NAACL-HLT.
12. Luong, M.-T., Pham, H., & Manning, C. D. (2015). Effective approaches to attention-based neural machine translation. In Proceedings of EMNLP.
13. 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.
14. Xu, X., Tu, W., & Yang, Y. (2023). CASE-Net: Integrating local and non-local attention operations for speech enhancement. Speech Communication, 148, 31-39.
15. 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.
16. Pei, Z., Huang, Q., & Wang, S. (2026). When LLMs develop languages: Symbolic communication for efficient multi-agent reasoning.arXiv preprint arXiv:2606.29354.
17. 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.
18. 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).
19. 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.
20. Xu, X., Xie, H., Qin, S. J., Li, L., Tao, X., & Wang, F. L. (2026). Delayed commitment for representation readiness in stage-wise audio-visual learning.arXiv preprint arXiv:2605.01673.
21. 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).
22. 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.
23. 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.
24. 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).
25. 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).
26. 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.
27. 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.
28. 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.
29. Xie, Z., Liao, R., Wang, Z., Chen, C., Hua, X. S., & Luo, X. (2026, July). GALA: Geometric Data Selection with Strategic Prospecting for Large Language Model Self-training. In Findings of the Association for Computational Linguistics: ACL 2026(pp. 10281-10293).
30. 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.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Zoé Mathieu, Adrien T. Roy (Author)

This work is licensed under a Creative Commons Attribution 4.0 International License.
All articles published in the International Journal of Information and Communication Technology Trends (IJICTT) are distributed under a Creative Commons license. This allows readers to freely access, share, and adapt the content for non-commercial purposes, provided proper attribution is given to the original authors. Authors retain copyright of their work.
