the open
    research
    Contribute
    Back to the reading lists

    Safety, alignment & interpretability· 2020

    Extracting Training Data from Large Language Models

    Nicholas Carlini (first author) · 2020 · published 2021

    Read the original

    arXiv 2012.07805OpenAlex W3112689365

    On the reading lists

    Why it matters

    Demonstrated extraction of memorized training examples and personal information from language models.

    Condensed from the expert lists' notes.

    The record

    First released
    2020 (from arXiv 2012.07805)
    Published
    2021
    Citations
    3,459 citations, as counted by Papers With Code (CC BY-SA 4.0)
    Named by
    the chatgpt list only
    Score
    0.308 · computed rank 585 · consensus 0.11, must-read 0, citations percentile 0.787 (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.