Back to papers
August 19, 2026cs.LGcs.AIcs.CL
Beyond Teacher Likelihood: Group-Calibrated On-Policy Distillation for Long-Context Reasoning
Zhu Zhang, Jixun Wang, Xiaoang Xu, Xiaorong Wang, Zihan Zhou, Zhiyuan Wang, Shuo Wang, Chaojun Xiao, Yuezhi Zhou
Categories
cs.LG, cs.AI, cs.CL