@inproceedings{lewis-lim-etal-2025-analysing,
    title = "Analysing Chain of Thought Dynamics: Active Guidance or Unfaithful Post-hoc Rationalisation?",
    author = "Lewis-Lim, Samuel  and
      Tan, Xingwei  and
      Zhao, Zhixue  and
      Aletras, Nikolaos",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.1516/",
    pages = "29826--29841",
    ISBN = "979-8-89176-332-6",
    abstract = "Recent work has demonstrated that using chain of thought (CoT), on soft-reasoning problems such as analytical and commonsense reasoning, often yields limited or even negative performance gains. CoT can also be unfaithful to the model{'}s actual reasoning. This paper investigates dynamics and unfaithfulness of CoT in soft-reasoning tasks across instruction-tuned, reasoning and reasoning-distilled models. Our findings show that distilled{-}reasoning models rely heavily on CoT for these tasks, while instruction{-}tuned and reasoning models often use it post{-}hoc. Additionally, we find that CoT can steer model predictions without faithfully reflecting reasoning, indicating a disconnect between CoT influence and faithfulness."
}