Explanation Generation On E Snli Ve
평가 지표
Human Explanation Rating
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | Human Explanation Rating | Paper Title | Repository |
|---|---|---|---|
| OFA-X | 85.7 | Harnessing the Power of Multi-Task Pretraining for Ground-Truth Level Natural Language Explanations | |
| OFA-X-MT | 80.4 | Harnessing the Power of Multi-Task Pretraining for Ground-Truth Level Natural Language Explanations |
0 of 2 row(s) selected.