Adaptive Teacher Exposure for Self-Distillation in LLM Reasoning 文章

ArXiv CS.CL2026-05-28NEWSen作者: Zihao Han, Tiangang Zhang, Huaibin Wang, Yilun Sun
查看原文 →
关系图谱

Adaptive Teacher Exposure for Self-Distillation in LLM Reasoning · 相关技术

相关技术

On-policy self-distillation