@inproceedings{tutek-etal-2025-measuring,
    title = "Measuring Chain of Thought Faithfulness by Unlearning Reasoning Steps",
    author = "Tutek, Martin  and
      Hashemi Chaleshtori, Fateme  and
      Marasovic, Ana  and
      Belinkov, Yonatan",
    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.504/",
    pages = "9946--9971",
    ISBN = "979-8-89176-332-6",
    abstract = "When prompted to think step-by-step, language models (LMs) produce a chain of thought (CoT), a sequence of reasoning steps that the model supposedly used to produce its prediction. Despite much work on CoT prompting, it is unclear if reasoning verbalized in a CoT is faithful to the models' parametric beliefs. We introduce a framework for measuring parametric faithfulness of generated reasoning and propose Faithfulness by Unlearning Reasoning steps (FUR), an instance of this framework. FUR erases information contained in reasoning steps from model parameters and measures faithfulness as the resulting effect on the model{'}s prediction. Our experiments with four LMs and five multi-choice question answering (MCQA) datasets show that FUR is frequently able to precisely change the underlying models' prediction for a given instance by unlearning key steps, indicating when a CoT is parametrically faithful. Further analysis shows that CoTs generated by models post-unlearning support different answers, hinting at a deeper effect of unlearning."
}