Decoupling the Effect of Chain-of-Thought Reasoning: A Human Label Variation Perspective
This work reveals a fundamental limitation of CoT reasoning for probabilistic tasks, showing it acts as a decisive decision-maker rather than a granular calibrator, which is important for understanding LLM behavior in ambiguous scenarios.
The paper investigates how Chain-of-Thought (CoT) reasoning affects human label variation tasks, finding that CoT improves distributional alignment but final accuracy is driven by CoT content (99% variance), while distributional ranking is governed by model priors (over 80%).
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.