the open
    research
    Contribute
    Back to the reading lists

    Language, speech & LLMs· 2023

    Toolformer: Language Models Can Teach Themselves to Use Tools

    Timo Schick (first author) · 2023

    Read the original

    DOI 10.52202/075280-2997arXiv 2302.04761OpenAlex W7133214447

    On the reading lists

    Why it matters

    Demonstrated self-supervised learning of when and how language models should call external APIs.

    Condensed from the expert lists' notes.

    The record

    First released
    2023 (from arXiv 2302.04761)
    Citations
    6,197 citations, as counted by Papers With Code (CC BY-SA 4.0)
    Named by
    both expert lists
    Score
    0.487 · computed rank 245 · consensus 0.51, must-read 0.5, citations percentile 0.812 (2020s · language), 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.