Proceedings

TriHAI: A Combination Enhanced Tri-Mode Deferral for Human-AI Team

Minhui Zhang, Xuehan Zhao, Xin Zhang, Jiaqi Liu, Zhiwen Yu, Bin Guo

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. Main Track. Pages 3746-3754.

https://doi.org/10.24963/ijcai.2026/417

Keywords

  • Humans and AI: Human-AI collaboration

Abstract

Learning to Defer operates by deferring AI-uncertain samples to humans, enabling the system to outperform either alone. Some works extend it by introducing human-AI combination to deferral. However, they remain limited to binary choices. Given that AI, humans, and human-AI combination are each indispensable, we extend the binary deferral paradigm to a ternary one. There are two challenges: i) how to effectively select among the three modes, especially distinguishing humans from combination? ii) how to design an enhanced combination without being degraded by unreliable model predictions? To address the challenges, we propose TriHAI, a tri-mode deferral method that routes samples to suitable modes based on normalized confidence scores obtained through a discriminative gating network, and enhances combination mode by fusing model predictions refined by human-guided Conformal Prediction and human predictions via Bayesian theory. Experiments on three datasets show that TriHAI surpasses other human-AI baselines by up to 9.57% in accuracy.

Minhui Zhang, Xuehan Zhao, Xin Zhang, Jiaqi Liu, Zhiwen Yu, and Bin Guo. 2026. TriHAI: A Combination Enhanced Tri-Mode Deferral for Human-AI Team. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 3746–3754. https://doi.org/10.24963/ijcai.2026/417
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards