Back to papers
April 14, 2026cs.LGcs.AIcs.CL
Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
Yaxuan Li, Yuxin Zuo, Bingxiang He, Jinqian Zhang, Chaojun Xiao, Cheng Qian, Tianyu Yu, Huan-ang Gao, Wenkai Yang, Zhiyuan Liu, Ning Ding
HF Upvotes
31
Categories
cs.LG, cs.AI, cs.CL