Extreme Summarization on GEM-XSum
Metric: ROUGE-2 (higher is better)
Metric: ROUGE-2 (higher is better)
| # | Model↕ | ROUGE-2▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | PEGASUS | 23.2 | No | The GEM Benchmark: Natural Language Generation, ... | 2021-02-02 | - |
| 2 | PaLM (finetuning)-540B | 21.2 | No | PaLM: Scaling Language Modeling with Pathways | 2022-04-05 | Code |
| 3 | T5-XXL | 21 | No | PaLM: Scaling Language Modeling with Pathways | 2022-04-05 | Code |
| 4 | PaLM (finetuning)-62B | 18.5 | No | PaLM: Scaling Language Modeling with Pathways | 2022-04-05 | Code |