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/CriSPO 3-shot

CriSPO 3-shot

Reported on 15 benchmarks across 2 tasks · 1 paper · 6 SOTA

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

Knowledge Base12 results

  • Text SummarizationonACI-Bench
    ROUGE-1· 2024-10-03
    63.1
    SOTA
    CriSPO: Multi-Aspect Critique-Suggestion-guided Automatic Prompt Optimization for Text GenerationarXiv:2410.02748
  • Text SummarizationonACI-Bench
    ROUGE-2· 2024-10-03
    32.5
    SOTA
    CriSPO: Multi-Aspect Critique-Suggestion-guided Automatic Prompt Optimization for Text GenerationarXiv:2410.02748
  • Text SummarizationonACI-Bench
    ROUGE-L· 2024-10-03
    41
    SOTA
    CriSPO: Multi-Aspect Critique-Suggestion-guided Automatic Prompt Optimization for Text GenerationarXiv:2410.02748
  • Text SummarizationonMeetingBank
    ROUGE-2· 2024-10-03
    46.5
    SOTA
    CriSPO: Multi-Aspect Critique-Suggestion-guided Automatic Prompt Optimization for Text GenerationarXiv:2410.02748
  • Text SummarizationonMeetingBank
    ROUGE-L· 2024-10-03
    54.1
    SOTA
    CriSPO: Multi-Aspect Critique-Suggestion-guided Automatic Prompt Optimization for Text GenerationarXiv:2410.02748
  • Text SummarizationonMeetingBank
    Rouge-1· 2024-10-03
    58.5
    SOTA
    CriSPO: Multi-Aspect Critique-Suggestion-guided Automatic Prompt Optimization for Text GenerationarXiv:2410.02748
  • Text SummarizationonSAMSum
    ROUGE-1· 2024-10-03
    47.2
    best: 59.1 (OmniVec2)
    CriSPO: Multi-Aspect Critique-Suggestion-guided Automatic Prompt Optimization for Text GenerationarXiv:2410.02748
  • Text SummarizationonSAMSum
    ROUGE-2· 2024-10-03
    20.8
    best: 34.1 (OmniVec2)
    CriSPO: Multi-Aspect Critique-Suggestion-guided Automatic Prompt Optimization for Text GenerationarXiv:2410.02748
  • Text SummarizationonSAMSum
    ROUGE-L· 2024-10-03
    38.2
    best: 63.7 (OmniVec2)
    CriSPO: Multi-Aspect Critique-Suggestion-guided Automatic Prompt Optimization for Text GenerationarXiv:2410.02748
  • Text SummarizationonCNN / Daily Mail
    ROUGE-L· 2024-10-03
    27.4
    best: 45.35 (Scrambled code + broken (alter))
    CriSPO: Multi-Aspect Critique-Suggestion-guided Automatic Prompt Optimization for Text GenerationarXiv:2410.02748
  • Text SummarizationonCNN/Daily Mail
    ROUGE-1· 2024-10-03
    42.1
    best: 44.47 (BART (TextBox 2.0))
    CriSPO: Multi-Aspect Critique-Suggestion-guided Automatic Prompt Optimization for Text GenerationarXiv:2410.02748
  • Text SummarizationonCNN/Daily Mail
    ROUGE-2· 2024-10-03
    17
    best: 21.5 (BART (TextBox 2.0))
    CriSPO: Multi-Aspect Critique-Suggestion-guided Automatic Prompt Optimization for Text GenerationarXiv:2410.02748

Natural Language Processing3 results

  • Abstractive Text SummarizationonCNN / Daily Mail
    ROUGE-L· 2024-10-03
    27.4
    best: 45.35 (Scrambled code + broken (alter))
    CriSPO: Multi-Aspect Critique-Suggestion-guided Automatic Prompt Optimization for Text GenerationarXiv:2410.02748
  • Abstractive Text SummarizationonCNN/Daily Mail
    ROUGE-1· 2024-10-03
    42.1
    best: 44.47 (BART (TextBox 2.0))
    CriSPO: Multi-Aspect Critique-Suggestion-guided Automatic Prompt Optimization for Text GenerationarXiv:2410.02748
  • Abstractive Text SummarizationonCNN/Daily Mail
    ROUGE-2· 2024-10-03
    17
    best: 21.5 (BART (TextBox 2.0))
    CriSPO: Multi-Aspect Critique-Suggestion-guided Automatic Prompt Optimization for Text GenerationarXiv:2410.02748