the open
    research
    Contribute
    Back to the reading lists

    Safety, alignment & interpretability· 2021

    Ethical and Social Risks of Harm from Language Models

    Weidinger (first author) · 2021

    Read the original

    arXiv 2112.04359OpenAlex W4226112058

    On the reading lists

    Why it matters

    Taxonomy of risks from large language models.

    Condensed from the expert lists' notes.

    The record

    First released
    2021 (from arXiv 2112.04359)
    Citations
    1,685 citations, as counted by Papers With Code (CC BY-SA 4.0)
    Named by
    the grok list only
    Score
    0.274 · computed rank 667 · consensus 0.12, must-read 0, citations percentile 0.681 (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.