Scaling Properties of Same-Family On-Policy Distillation
*Reinforcement learning (RL)* can induce substantial reasoning capabilities in large language models (LLMs), but how much of this capability transfers across model scales, and how quickly, remains unclear. We study the scaling properties of *on-policy distillation (OPD)* across *weak-to-strong*, *same-base*, and *stron...
Yun-Tai Bao, Qin-Feng Li, Guo-qing Jiang et al.
· 0 citations