Explanation Generation On Vqa X
Metrics
Human Explanation Rating
Results
Performance results of various models on this benchmark
Model Name | Human Explanation Rating | Paper Title | Repository |
|---|---|---|---|
| OFA-X | 89.5 | Harnessing the Power of Multi-Task Pretraining for Ground-Truth Level Natural Language Explanations | |
| OFA-X-MT | 87.8 | Harnessing the Power of Multi-Task Pretraining for Ground-Truth Level Natural Language Explanations |
0 of 2 row(s) selected.