@inproceedings{mitsuhashi-etal-2026-disentangling,
    title = "Disentangling the Effects of Unlearning in Measuring Parametric Faithfulness of Chain-of-Thought",
    author = "Mitsuhashi, Ryo  and
      Morio, Gaku  and
      Niwa, Ayana  and
      Kaneko, Masahiro  and
      Inui, Kentaro  and
      Morishita, Terufumi  and
      Koreeda, Yuta  and
      Sogawa, Yasuhiro",
    editor = "T.Y.S.S., Santosh  and
      Rodriguez, Juan Diego  and
      de Gibert, Ona",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics ({ACL} 2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-srw.36/",
    pages = "413--419",
    ISBN = "979-8-89176-393-7",
    abstract = "Chain-of-Thought (CoT) in large language models (LLMs) has been widely debated in terms of whether it faithfully reflects an internal reasoning process of models. Parametric faithfulness is a recently proposed metric that uses unlearning to assess whether a model encodes parametric beliefs corresponding to a reasoning chain. This paper refines this metric by accounting for the unintended artifacts of unlearning. We introduce control tasks that unlearn irrelevant knowledge and word-shuffled content and show that these control tasks yield substantial parametric faithfulness values, suggesting the non-negligible effect of unlearning. We also found that control tasks help explain the significant variations in parametric faithfulness observed across different model sizes and CoT lengths. We conclude that the effects of unlearning need to be considered when measuring parametric faithfulness."
}