pith. the verified trust layer for science. sign in

Title resolution pending

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CY 1

years

2020 1

verdicts

ACCEPT 1

representative citing papers

Measuring Massive Multitask Language Understanding

cs.CY · 2020-09-07 · accept · novelty 8.0

Introduces the MMLU benchmark of 57 tasks and shows that current models, including GPT-3, achieve low accuracy far below expert level across academic and professional domains.

citing papers explorer

Showing 1 of 1 citing paper.

  • Measuring Massive Multitask Language Understanding cs.CY · 2020-09-07 · accept · none · ref 61

    Introduces the MMLU benchmark of 57 tasks and shows that current models, including GPT-3, achieve low accuracy far below expert level across academic and professional domains.