解耦链式推理的影响：从人类标签变异视角出发
Decoupling the Effect of Chain-of-Thought Reasoning: A Human Label Variation Perspective
AI总结：
本文通过系统解耦实验探讨了链式推理对分布任务的影响，发现推理内容对最终准确性贡献大，而模型先验对分布排名起主导作用。
摘要：
利用长链式推理（CoT）的推理调优LLM在单答案任务中表现优异，但其对人类标签变异建模的能力仍待探索。本文通过分布基任务的系统解耦实验，采用交叉CoT实验分离推理文本与模型先验的影响。观察到一种明显的'解耦机制'：虽然CoT提升分布对齐，但最终准确性由CoT内容（贡献99%方差）决定，而分布排名由模型先验（超过80%）主导。逐步分析进一步显示，虽然推理过程中CoT对准确性的影响呈单调增长，但分布结构主要由LLM的内在先验决定。这些发现表明，长CoT是LLM在顶层选项中的决定性因素，但无法作为模糊任务的精细分布校准器。
英文摘要：
Reasoning-tuned LLMs utilizing long Chain-of-Thought (CoT) excel at single-answer tasks, yet their ability to model Human Label Variation--which requires capturing probabilistic ambiguity rather than resolving it--remains underexplored. We investigate this through systematic disentanglement experiments on distribution-based tasks, employing Cross-CoT experiments to isolate the effect of reasoning text from intrinsic model priors. We observe a distinct "decoupled mechanism": while CoT improves distributional alignment, final accuracy is dictated by CoT content (99% variance contribution), whereas distributional ranking is governed by model priors (over 80%). Step-wise analysis further shows that while CoT's influence on accuracy grows monotonically during the reasoning process, distributional structure is largely determined by LLM's intrinsic priors. These findings suggest that long CoT serves as a decisive LLM decision-maker for the top option but fails to function as a granular distribution calibrator for ambiguous tasks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
