Analysing Chain Of Thought Dynamics: Active Guidance Or Unfaithful Post-hoc Rationalisation? | Awesome LLM Papers Add your paper to Awesome LLM Papers

Analysing Chain Of Thought Dynamics: Active Guidance Or Unfaithful Post-hoc Rationalisation?

Samuel Lewis-Lim, Xingwei Tan, Zhixue Zhao, Nikolaos Aletras . No Venue 2025

[Paper]   Search on Google Scholar   Search on Semantic Scholar
Compositional Generalization Prompting

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.

Similar Work