the open
    research
    Contribute
    Back to the reading lists

    Safety, alignment & interpretability· 2023

    Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting

    Miles Turpin (first author) · 2023

    Read the original

    DOI 10.52202/075280-3275arXiv 2305.04388OpenAlex W7133228402

    On the reading lists

    Why it matters

    Demonstrated that generated reasoning can conceal actual influences on language-model answers.

    Condensed from the expert lists' notes.

    The record

    First released
    2023 (from arXiv 2305.04388)
    Citations
    1,875 citations, as counted by Papers With Code (CC BY-SA 4.0)
    Named by
    the chatgpt list only
    Score
    0.274 · computed rank 668 · consensus 0.02, must-read 0, citations percentile 0.766 (2020s · safety), awards 0, existing lists 0. Method

    Data sources

    Catalogue data from OpenAlex (CC0), Crossref (CC0 metadata; no abstracts are shown), arXiv, and Papers With Code (CC BY-SA 4.0). Each count names its source. See the method.