TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/Finetuned Transformer LM

Finetuned Transformer LM

Reported on 7 benchmarks across 2 tasks

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing10 results

  • Question AnsweringonRACE
    RACE
    59
    best: 81.75 (XLNet)
  • Question AnsweringonRACE
    RACE-h
    57.4
    best: 69.6 (OCN_large)
  • Question AnsweringonRACE
    RACE-m
    62.9
    best: 85.45 (XLNet)
  • Question AnsweringonStoryCloze
    Accuracy
    86.5
    best: 96.3 (BLOOMZ)
  • Natural Language InferenceonSciTail
    Accuracy
    88.3
    best: 96.8 (CA-MTL)
  • Natural Language InferenceonSciTail
    Accuracy
    88.3
    best: 96.8 (CA-MTL)
  • Natural Language InferenceonMultiNLI
    Matched
    82.1
    best: 92.6 (Turing NLR v5 XXL 5.4B (fine-tuned))
  • Natural Language InferenceonMultiNLI
    Mismatched
    81.4
    best: 92.4 (Turing NLR v5 XXL 5.4B (fine-tuned))
  • Natural Language InferenceonMultiNLI
    Matched
    82.1
    best: 92.6 (Turing NLR v5 XXL 5.4B (fine-tuned))
  • Natural Language InferenceonMultiNLI
    Mismatched
    81.4
    best: 92.4 (Turing NLR v5 XXL 5.4B (fine-tuned))