| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Summarization | CNN/DM | ROUGE-156.22 | 56 | |
| Membership Inference Attack | CNN-DM | AUC0.974 | 36 | |
| Summarization | CNN/DM | M Score10.64 | 35 | |
| Summarization | CNN/DM | Speedup3.58 | 32 | |
| Readability Style Transfer | CNN/DM (test) | FRE Delta27.42 | 25 | |
| Text summarization | CNN/DM | TPS Score217.02 | 20 | |
| Summarization | CNN/DM | Spd Score1.9 | 18 | |
| Extractive Summarization | CNN/DM (test) | ROUGE-152.59 | 18 | |
| Text Summarization | CNN/DM | ROUGE-216.95 | 16 | |
| Summarization | CNN-DM | Context Influence149.33 | 15 | |
| Input OOD Detection | CNN/DM | AUROC99.89 | 14 | |
| Abstractive Summarization | CNN/DM | ROUGE-142.05 | 14 | |
| Summarization Faithfulness | CNN/DM | SummaC52.85 | 12 | |
| Abstractive Summarization | CNN/DM sampled (test) | ROUGE Score22.86 | 12 | |
| Summarization | CNN/DM (test) | ROUGE23.39 | 12 | |
| Faithfulness Evaluation | CNN/DM (test) | SummaC35.56 | 12 | |
| Summarization | CNN/DM | Completeness Score5 | 12 | |
| Unsupervised abstractive summarization | CNN/DM (test) | ROUGE-140.13 | 12 | |
| Faithfulness Evaluation | CNN/DM | AUPC33.2 | 12 | |
| Summarization | CNN/DM (test) | Tau4.54 | 11 | |
| Summarization | CNN/DM (test) | ROUGE-144.54 | 11 | |
| Summarization | CNN/DM non-anonymized (test) | ROUGE-1100 | 10 | |
| Evaluating Context Influence and Input Regurgitation | CNN-DM | Information Influence (\hat{I})140 | 9 | |
| Summarization | CNN/DM | Speedup2.3 | 8 | |
| Summarization | CNN/DM | BERTScore0.89 | 8 |