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/PaLM 2 (few-shot, k=3, CoT)

PaLM 2 (few-shot, k=3, CoT)

Reported on 11 benchmarks across 3 tasks · 1 paper · 6 SOTA

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

Natural Language Processing7 results

  • Question AnsweringonBIG-bench (Movie Recommendation)
    Accuracy· 2023-05-17
    94.4
    SOTA
    PaLM 2 Technical ReportarXiv:2305.10403
  • Question AnsweringonBIG-bench (Navigate)
    Accuracy· 2023-05-17
    91.2
    SOTA
    PaLM 2 Technical ReportarXiv:2305.10403
  • Common Sense ReasoningonBIG-bench (Date Understanding)
    Accuracy· 2023-05-17
    91.2
    SOTA
    PaLM 2 Technical ReportarXiv:2305.10403
  • Question AnsweringonBIG-bench (Ruin Names)
    Accuracy· 2023-05-17
    83.6
    best: 90 (PaLM 2 (few-shot, k=3, Direct))
    PaLM 2 Technical ReportarXiv:2305.10403
  • Question AnsweringonBIG-bench (Hyperbaton)
    Accuracy· 2023-05-17
    82.4
    best: 92 (Bloomberg GPT (few-shot, k=3))
    PaLM 2 Technical ReportarXiv:2305.10403
  • Common Sense ReasoningonBIG-bench (Causal Judgment)
    Accuracy· 2023-05-17
    58.8
    best: 62 (PaLM 2 (few-shot, k=3, Direct))
    PaLM 2 Technical ReportarXiv:2305.10403
  • Common Sense ReasoningonBIG-bench (Disambiguation QA)
    Accuracy· 2023-05-17
    77.6
    best: 78.8 (PaLM 2 (few-shot, k=3, Direct))
    PaLM 2 Technical ReportarXiv:2305.10403

Methodology4 results

  • Logical ReasoningonBIG-bench (Penguins In A Table)
    Accuracy· 2023-05-17
    84.9
    SOTA
    PaLM 2 Technical ReportarXiv:2305.10403
  • Logical ReasoningonBIG-bench (Temporal Sequences)
    Accuracy· 2023-05-17
    100
    SOTA
    PaLM 2 Technical ReportarXiv:2305.10403
  • Logical ReasoningonBIG-bench (Reasoning About Colored Objects)
    Accuracy· 2023-05-17
    91.2
    SOTA
    PaLM 2 Technical ReportarXiv:2305.10403
  • Logical ReasoningonBIG-bench (Formal Fallacies Syllogisms Negation)
    Accuracy· 2023-05-17
    57.2
    best: 64.8 (PaLM 2 (few-shot, k=3, Direct))
    PaLM 2 Technical ReportarXiv:2305.10403