分析思維鏈動態：主動引導還是事後不忠的合理化？

摘要

近期研究表明，在分析性和常識推理等軟性推理問題上，思維鏈（Chain-of-Thought, CoT）往往帶來的增益有限。此外，CoT可能與模型的實際推理過程不一致。我們探討了在指令微調模型、推理模型及推理蒸餾模型中，CoT在軟性推理任務中的動態特性與忠實性。我們的研究揭示了這些模型依賴CoT的方式存在差異，並表明CoT的影響力與其忠實性並非總是保持一致。

English

Recent work has demonstrated that Chain-of-Thought (CoT) often yields limited gains for soft-reasoning problems such as analytical and commonsense reasoning. CoT can also be unfaithful to a model's actual reasoning. We investigate the dynamics and faithfulness of CoT in soft-reasoning tasks across instruction-tuned, reasoning and reasoning-distilled models. Our findings reveal differences in how these models rely on CoT, and show that CoT influence and faithfulness are not always aligned.

分析思維鏈動態：主動引導還是事後不忠的合理化？

Analysing Chain of Thought Dynamics: Active Guidance or Unfaithful Post-hoc Rationalisation?

摘要

Support