BALTO: Balanced Token-Level Policy Optimization for Hallucination Mitigation 文章

ArXiv CS.CL2026-06-16NEWSen作者: Ning Li, Zixuan Guo, Yan Xu, Wenbo Fei, Yifan Niu, Chang Luo, Yasheng Wang, Weiwen Liu, Yong Yu, Weinan Zhang
查看原文 →
关系图谱

BALTO: Balanced Token-Level Policy Optimization for Hallucination Mitigation · 相关技术

相关技术

reinforcement learninglarge language models