Retain Set
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Multimodal Machine Unlearning | Retain Set | Classification Accuracy48.13 | 35 | |
| Instruction Following | Retain set | Instruction Following Accuracy99 | 12 | |
| Multimodal Knowledge Retention | Retain-Set 15% forgetting ratio experiment | Classification VQA Accuracy61.6 | 7 | |
| Multimodal Knowledge Retention | Retain-Set 5% forgetting ratio experiment | Accuracy (Class VQA)61.56 | 7 |
Showing 4 of 4 rows