PEGASUS 2B + SliC

Reported on 3 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.

Knowledge Base3 results

Text SummarizationonSAMSum
ROUGE-1· 2022-09-30
54.37
best: 59.1 (OmniVec2)
SOTA
Calibrating Sequence likelihood Improves Conditional Language Generation arXiv:2210.00045
Text SummarizationonSAMSum
ROUGE-2· 2022-09-30
29.88
best: 34.1 (OmniVec2)
SOTA
Calibrating Sequence likelihood Improves Conditional Language Generation arXiv:2210.00045
Text SummarizationonSAMSum
ROUGE-L· 2022-09-30
45.89
best: 63.7 (OmniVec2)
Calibrating Sequence likelihood Improves Conditional Language Generation arXiv:2210.00045