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/UnifiedQA 3B

UnifiedQA 3B

Reported on 10 benchmarks across 1 task · 2 papers · 7 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 AnsweringonTruthfulQA
    % true· 2021-09-08
    53.86
    best: 88.6 (Vicuna 7B + Inference Time Intervention (ITI))
    SOTA
    TruthfulQA: Measuring How Models Mimic Human FalsehoodsarXiv:2109.07958
  • Question AnsweringonTruthfulQA
    % true (GPT-judge)· 2021-09-08
    53.24
    SOTA
    TruthfulQA: Measuring How Models Mimic Human FalsehoodsarXiv:2109.07958
  • Question AnsweringonTruthfulQA
    BLEU· 2021-09-08
    -0.16
    SOTA
    TruthfulQA: Measuring How Models Mimic Human FalsehoodsarXiv:2109.07958
  • Question AnsweringonTruthfulQA
    BLEURT· 2021-09-08
    0.08
    SOTA
    TruthfulQA: Measuring How Models Mimic Human FalsehoodsarXiv:2109.07958
  • Question AnsweringonTruthfulQA
    ROUGE· 2021-09-08
    1.76
    SOTA
    TruthfulQA: Measuring How Models Mimic Human FalsehoodsarXiv:2109.07958
  • Question AnsweringonSIQA
    Accuracy· 2020-05-02
    79.8
    best: 83.2 (Unicorn 11B (fine-tuned))
    SOTA
    UnifiedQA: Crossing Format Boundaries With a Single QA SystemarXiv:2005.00700
  • Question AnsweringonPIQA
    Accuracy· 2020-05-02
    85.3
    best: 90.1 (Unicorn 11B (fine-tuned))
    SOTA
    UnifiedQA: Crossing Format Boundaries With a Single QA SystemarXiv:2005.00700
  • Question AnsweringonTruthfulQA
    % info· 2021-09-08
    64.5
    best: 97.7 (Alpaca 7B + Inference Time Intervention (ITI))
    TruthfulQA: Measuring How Models Mimic Human FalsehoodsarXiv:2109.07958
  • Question AnsweringonTruthfulQA
    MC1· 2021-09-08
    0.19
    best: 0.59 (GPT-4 (RLHF))
    TruthfulQA: Measuring How Models Mimic Human FalsehoodsarXiv:2109.07958
  • Question AnsweringonTruthfulQA
    MC2· 2021-09-08
    0.35
    best: 0.75 (Mistral-7B-Instruct-v0.2 + TruthX)
    TruthfulQA: Measuring How Models Mimic Human FalsehoodsarXiv:2109.07958