Metric: ROUGE-2 (higher is better)
| # | Model↕ | ROUGE-2▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | MUPPET BART Large | 11.25 | Yes | Muppet: Massive Multi-task Representations with ... | 2021-01-26 | Code |
| 2 | PEGASUS 2B + SLiC | 11.13 | No | Calibrating Sequence likelihood Improves Conditi... | 2022-09-30 | - |
| 3 | BART+R3F | 10.98 | No | Better Fine-Tuning by Reducing Representational ... | 2020-08-06 | Code |
| 4 | PEGASUS + SummaReranker | 9.5 | No | SummaReranker: A Multi-Task Mixture-of-Experts R... | 2022-03-13 | Code |
| 5 | MatchSum | 6.17 | No | Extractive Summarization as Text Matching | 2020-04-19 | Code |