Token-Importance Guided Direct Preference Optimization
作者:Ning Yang, Hai Lin, Yibo Liu, Baoliang Tian, Guoqing Liu, Haijun Zhang · 单位:Institute of Automation, Chinese Academy of Sciences, The Chinese University of Hong Kong, Shenzhen, Microsoft Research AI4Science, University of Science and Technology Beijing · 来源:arXiv · 发布日期:2025-05-26