OGLS-SD: On-Policy Self-Distillation with Outcome-Guided Logit Steering for LLM Reasoning 文章

ArXiv CS.AI2026-06-02NEWSen作者: Yuxiao Yang, Xiaoyun Wang, Weitong Zhang
查看原文 →
关系图谱

OGLS-SD: On-Policy Self-Distillation with Outcome-Guided Logit Steering for LLM Reasoning · 相关技术

相关技术

On-policy self-distillationOGLS-SDPSD