the open
    research
    Contribute
    Back to the reading lists

    Safety, alignment & interpretability· 2022

    Language Models (Mostly) Know What They Know

    Kadavath (first author) · 2022

    Read the original

    arXiv 2207.05221OpenAlex W4285429195

    On the reading lists

    Why it matters

    Studied self-evaluation and calibration in language models.

    Condensed from the expert lists' notes.

    The record

    First released
    2022 (from arXiv 2207.05221)
    Citations
    2,170 citations, as counted by Papers With Code (CC BY-SA 4.0)
    Named by
    the grok list only
    Score
    0.321 · computed rank 554 · consensus 0.2, must-read 0, citations percentile 0.745 (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.