the open
    research
    Contribute
    Back to the reading lists

    Safety, alignment & interpretability· 2022

    Discovering Language Model Behaviors with Model-Written Evaluations

    Perez (first author) · 2022

    Read the original

    arXiv 2212.09251OpenAlex W4385571158

    On the reading lists

    Why it matters

    Used model-written tests to surface emergent behaviors.

    Condensed from the expert lists' notes.

    The record

    First released
    2022 (from arXiv 2212.09251)
    Citations
    1,121 citations, as counted by Papers With Code (CC BY-SA 4.0)
    Named by
    the grok list only
    Score
    0.264 · computed rank 694 · consensus 0.21, must-read 0, citations percentile 0.574 (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.