Next-token Prediction

Next-Token Prediction is a computational task in language modeling where the objective is to predict the most probable subsequent token in a sequence given its preceding context, serving as the foundational training paradigm for autoregressive language models.

68

Publications

7.3K

Citations

1.1K

Authors

83

Institutions

Publications per year

2017–2026

63

Variants

Next Token Prediction

Authors

1.1K

  1. PG
    Petko Georgiev

    University of Cambridge, United Kingdom

    2 publications · 419 citations

    2

    h-index

  2. EF
    Evelina Fedorenko

    Massachusetts Institute of Technology, United States

    2 publications · 65 citations

    2

    h-index

  3. MZ
    Ming Zhang

    Chinese Academy of Sciences, China

    2 publications · 419 citations

    2

    h-index

  4. YW
    Yonghui Wu

    Google (United States), United States

    2 publications · 377 citations

    2

    h-index

  5. DR
    Dominika Rogozińska

    Heliodor Swiecicki Clinical Hospital, Poland

    2 publications · 419 citations

    2

    h-index

1–5 of 1.1K

Venues

  1. arXiv (Cornell University)

    Repository · 29 publications · 5.4K citations

    20

    h-index

  2. ChemRxiv

    Repository · 2 publications · 29 citations

    2

    h-index

  3. IEEE Intelligent Systems

    1 publications · 114 citations

    1

    h-index

  4. Nature Machine Intelligence

    1 publications · 24 citations

    1

    h-index

  5. 1

    h-index

1–5