Adaptive Preference Optimization with Uncertainty-aware Utility Anchor 文章

ArXiv CS.CL2026-05-26NEWSen作者: Xiaobo Wang, Zixia Jia, Jiaqi Li, Qi Liu, Zilong Zheng
查看原文 →
关系图谱

Adaptive Preference Optimization with Uncertainty-aware Utility Anchor · 相关技术

相关技术

Adaptive Preference Optimization with Utility AnchorBradley-Terry reward modelingDirect Preference Optimizationlarge language models