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/GPT-2 1.5B

GPT-2 1.5B

Reported on 8 benchmarks across 1 task · 1 paper · 2 SOTA

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

Natural Language Processing8 results

  • Question AnsweringonTruthfulQA
    MC1· 2021-09-08
    0.22
    best: 0.59 (GPT-4 (RLHF))
    SOTA
    TruthfulQA: Measuring How Models Mimic Human FalsehoodsarXiv:2109.07958
  • Question AnsweringonTruthfulQA
    MC2· 2021-09-08
    0.39
    best: 0.75 (Mistral-7B-Instruct-v0.2 + TruthX)
    SOTA
    TruthfulQA: Measuring How Models Mimic Human FalsehoodsarXiv:2109.07958
  • Question AnsweringonTruthfulQA
    % info· 2021-09-08
    89.84
    best: 97.7 (Alpaca 7B + Inference Time Intervention (ITI))
    TruthfulQA: Measuring How Models Mimic Human FalsehoodsarXiv:2109.07958
  • Question AnsweringonTruthfulQA
    % true· 2021-09-08
    29.5
    best: 88.6 (Vicuna 7B + Inference Time Intervention (ITI))
    TruthfulQA: Measuring How Models Mimic Human FalsehoodsarXiv:2109.07958
  • Question AnsweringonTruthfulQA
    % true (GPT-judge)· 2021-09-08
    29.87
    best: 53.24 (UnifiedQA 3B)
    TruthfulQA: Measuring How Models Mimic Human FalsehoodsarXiv:2109.07958
  • Question AnsweringonTruthfulQA
    BLEU· 2021-09-08
    -4.91
    best: -0.16 (UnifiedQA 3B)
    TruthfulQA: Measuring How Models Mimic Human FalsehoodsarXiv:2109.07958
  • Question AnsweringonTruthfulQA
    BLEURT· 2021-09-08
    -0.25
    best: 0.08 (UnifiedQA 3B)
    TruthfulQA: Measuring How Models Mimic Human FalsehoodsarXiv:2109.07958
  • Question AnsweringonTruthfulQA
    ROUGE· 2021-09-08
    -9.41
    best: 1.76 (UnifiedQA 3B)
    TruthfulQA: Measuring How Models Mimic Human FalsehoodsarXiv:2109.07958