Reinforcement learning with verifiable rewards (RLVR) controls policy entropy by reweighting tokens against an external scalar advantage. On-policy distillation (OPD) faces the same surface problem, a student that can sharpen too fast, but it replaces that advantage with a per-token teacher target. That shared symptom...
Xian-Kun Lin, Zhe-Zheng Hao, Li-Xin Liu et al.· 0 citations
Learning from interaction experience is essential for enabling large language models to continually improve during deployment. Context distillation offers a promising path: privileged information extracted from experience is provided to a teacher, whose behavior is then distilled into a student model that has no access...
Zhe-Zheng Hao, Yong-Kang Yang, Xia-Ling-Zhang-Yu-Xin Xia et al.· 0 citations
Unified On-Policy Self-Distillation (USD), a lightweight online algorithm to solve the Lagrangian, reveals that a single dual variable governs both decisions: at one price for learning difficulty, it simultaneously sets the token-selection threshold and the direction of privileged-information adjustment, keeping superv...
Yongkang Yang, Zhezheng Hao, Hong Zhang et al.· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
