OPD2 min read
ATI-OPD: Adaptive Teacher Intervention for Stable Long-Sequence On-Policy Distillation
On-policy distillation (OPD) trains a student on its own responses using token-level feedback from a teacher. As responses grow longer, the student's prefix can depart from the teacher's own reasoning, weakening its feedback on later tokens.
By Jiannan Guan, Youxin Jiang, Yutai Hou, Qiguang Chen, Yirong Zeng, Haitao Wang, Dengyun Peng, Zheng Yan, Jinhao Liu, Tao Ye, Dandan Tu, Wanxiang ChearXiv - cs.CL (NLP)
Read the full story
Originally published by arXiv - cs.CL (NLP) on Oct 30, 2026.
Comments
Sign in to join the discussion.