the open
    research
    Contribute
    Back to the reading lists

    Safety, alignment & interpretability· 2022

    Locating and Editing Factual Associations in GPT

    Kevin Meng (first author) · 2022

    Read the original

    arXiv 2202.05262OpenAlex W4281657280

    On the reading lists

    Why it matters

    Localized factual recall mechanisms and demonstrated targeted editing of stored language-model associations.

    Condensed from the expert lists' notes.

    The record

    First released
    2022 (from arXiv 2202.05262)
    Citations
    3,485 citations, as counted by Papers With Code (CC BY-SA 4.0)
    Named by
    both expert lists
    Score
    0.388 · computed rank 384 · consensus 0.25, must-read 0, citations percentile 0.894 (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.