the open
    research
    Contribute
    Back to the reading lists

    Language, speech & LLMs· 2022

    Training Compute-Optimal Large Language Models

    Jordan Hoffmann (first author) · 2022

    Read the original

    DOI 10.52202/068431-2176arXiv 2203.15556OpenAlex W7133225605

    On the reading lists

    Why it matters

    Revolutionized training budgets by demonstrating the importance of balancing parameters and training tokens.

    Condensed from the expert lists' notes.

    The record

    First released
    2022 (from arXiv 2203.15556)
    Citations
    3,889 citations, as counted by Papers With Code (CC BY-SA 4.0)
    Named by
    both expert lists
    Also relevant to
    Deep learning
    Score
    0.588 · computed rank 162 · consensus 0.92, must-read 1, citations percentile 0.604 (2020s · language), awards 0, existing lists 0. Method

    Editor's notes

    • Readability check: pass: Chinchilla: how to split compute between model size and data. (AI draft (Claude), not yet reviewed, 2026-10-29)

    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.