研究定位 CoT 可控性受推理开头 token 限制
一项研究发现，CoT 监控部分依赖模型无法控制推理内容，而这一限制主要与思考标签后的前几个 token 有关。禁用高频开头 token 并加入上下文示例后，各模型平均指令遵循率提升 34 至 41 个百分点，但对省略信息的控制改善较不稳定。论文链接：https://arxiv.org/abs/2610.40939
Nice paper on CoT controllability.
They find that chain-of-thought monitoring depends partly on models being unable to control what they write in their reasoning.
They traced much of that limit to the first few tokens after the opening thinking tag. Entropy collapses there, and the model falls into a few common openings.
Small changes at that point restore a lot of control. Prefilling a single token raised controllability substantially. Banning frequent opening tokens and adding in-context examples raised average compliance by 34 to 41 points across models.
These interventions mostly restore control over adding or restyling information. Control over leaving information out responded less consistently.
The two kinds behave like separate capabilities. Across models, scores correlate within each group and mostly negatively between groups.
arxiv.org/abs/2610.40939
Chat with Paper: academy.dair.ai/papers/the-f…
来源：omarsar0 · x.com