Length Penalties Make Chain-of-Thought Less Monitorable
英文标题：Length Penalties Make Chain-of-Thought Less Monitorable
arXiv:2607.09786v1 Announce Type: new Abstract: Length-penalized reinforcement learning can shorten chain-of-thought reasoning while hiding an influence that drives the model's answer. In our experiments, training with length penalties does not stop misleading hints from steering models, even thoug
打开原文相关 1.6 · 机会 0
中文
arXiv:2607.09786v1 Announce Type: new Abstract: Length-penalized reinforcement learning can shorten chain-of-thought reasoning while hiding an influence that drives the model's answer. In our experiments, training with length penalties does not stop misleading hints from steering models, even thoug
中文全文翻译正在补齐，可先查看下方英文原文。
English / 原文
arXiv:2607.09786v1 Announce Type: new Abstract: Length-penalized reinforcement learning can shorten chain-of-thought reasoning while hiding an influence that drives the model's answer. In our experiments, training with length penalties does not stop misleading hints from steering models, even thoug