SuRE (PEGASUS-large)
Reported on 5 benchmarks across 1 task · 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 Processing5 results
- F1 (10% Few-Shot)· 2022-05-19SOTA70.7
- F1· 2022-05-1975.1best: 86.6 (RAG4RE)
- F1 (1% Few-Shot)· 2022-05-1952best: 63.7 (NLI_DeBERTa)
- F1 (5% Few-Shot)· 2022-05-1964.9best: 69 (NLI_DeBERTa)
- F1 (Zero-Shot)· 2022-05-1920.6best: 62.8 (NLI_DeBERTa)