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/Flipped-3B

Flipped-3B

Reported on 10 benchmarks across 6 tasks · 1 paper · 1 SOTA

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

Natural Language Processing10 results

  • Question AnsweringonStoryCloze
    Accuracy· 2022-10-06
    95.88
    best: 96.3 (BLOOMZ)
    SOTA
    Guess the Instruction! Flipped Learning Makes Language Models Stronger Zero-Shot LearnersarXiv:2210.02969
  • Question AnsweringonCOPA
    Accuracy· 2022-10-06
    89.88
    best: 100 (PaLM 540B (finetuned) )
    Guess the Instruction! Flipped Learning Makes Language Models Stronger Zero-Shot LearnersarXiv:2210.02969
  • Common Sense ReasoningonWinoGrande
    Accuracy· 2022-10-06
    58.56
    best: 96.1 (ST-MoE-32B 269B (fine-tuned))
    Guess the Instruction! Flipped Learning Makes Language Models Stronger Zero-Shot LearnersarXiv:2210.02969
  • Word Sense DisambiguationonWords in Context
    Accuracy· 2022-10-06
    50.42
    best: 85.3 (COSINE + Transductive Learning)
    Guess the Instruction! Flipped Learning Makes Language Models Stronger Zero-Shot LearnersarXiv:2210.02969
  • Natural Language InferenceonANLI test
    A1· 2022-10-06
    39.99
    best: 81.8 (T5-3B (explanation prompting))
    Guess the Instruction! Flipped Learning Makes Language Models Stronger Zero-Shot LearnersarXiv:2210.02969
  • Natural Language InferenceonANLI test
    A2· 2022-10-06
    37.05
    best: 72.5 (T5-3B (explanation prompting))
    Guess the Instruction! Flipped Learning Makes Language Models Stronger Zero-Shot LearnersarXiv:2210.02969
  • Natural Language InferenceonANLI test
    A3· 2022-10-06
    37.73
    best: 74.8 (T5-3B (explanation prompting))
    Guess the Instruction! Flipped Learning Makes Language Models Stronger Zero-Shot LearnersarXiv:2210.02969
  • Natural Language InferenceonRTE
    Accuracy· 2022-10-06
    71.05
    best: 86.8 (PSQ (Chen et al., 2020))
    Guess the Instruction! Flipped Learning Makes Language Models Stronger Zero-Shot LearnersarXiv:2210.02969
  • Coreference ResolutiononWinograd Schema Challenge
    Accuracy· 2022-10-06
    58.37
    best: 100 (PaLM 540B (fine-tuned))
    Guess the Instruction! Flipped Learning Makes Language Models Stronger Zero-Shot LearnersarXiv:2210.02969
  • Sentence CompletiononHellaSwag
    Accuracy· 2022-10-06
    41.6
    best: 96.1 (CompassMTL 567M with Tailor)
    Guess the Instruction! Flipped Learning Makes Language Models Stronger Zero-Shot LearnersarXiv:2210.02969