the open
    research
    Contribute
    Back to the reading lists

    Safety, alignment & interpretability· 2023

    Jailbroken: How Does LLM Safety Training Fail?

    Alexander Wei (first author) · 2023

    Read the original

    DOI 10.52202/075280-3508arXiv 2307.02483OpenAlex W7133204634

    On the reading lists

    Why it matters

    Identified competing objectives and mismatched generalization as fundamental jailbreak failure modes.

    Condensed from the expert lists' notes.

    The record

    First released
    2023 (from arXiv 2307.02483)
    Citations
    2,283 citations, as counted by Papers With Code (CC BY-SA 4.0)
    Named by
    the chatgpt list only
    Score
    0.319 · computed rank 561 · consensus 0.07, must-read 0, citations percentile 0.851 (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.