Xu, Yifan, Xichen Ye, Yifan Chen, and Qiaosheng Zhang. 2026. “When Human Preferences Flip: An Instance-Dependent Robust Loss for RLHF”. Proceedings of the AAAI Conference on Artificial Intelligence 40 (44):38057-65. https://doi.org/10.1609/aaai.v40i44.41143.