Analysing Chain of Thought Dynamics: Active Guidance or Unfaithful Post-hoc Rationalisation?
Samuel Lewis-Lim, Xingwei Tan, Zhixue Zhao, and 1 more author
In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, Aug 2025
(Accepted to EMNLP 2025 Main Conference)
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.