| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| MUSE-News 1.0 (test) | GA | Exact Memoriation0 | 46 | 4d ago | |
| Syntax-preserving dataset (forget set) | GA | PrivLeak0.51 | 40 | 4d ago | |
| MUSE-Books Harry Potter forget set 500 samples | R-Forget-50039.99 | 13 | 4d ago | ||
| MUSE-Books Harry Potter 100 samples (forget set) | R-Forget32.13 | 13 | 4d ago | ||
| ToFU | Probability0.9908 | 10 | 4d ago | ||
| TOFU (forget01) | OBLIVIATE | Forgetting Quality (F.Q.)92 | 10 | 4d ago | |
| CIFAR-10 Random Forget (50%) | Unlearn Acc100 | 9 | 4d ago | ||
| CIFAR-10 Random Forget (10%) | SalUn | Unlearn Accuracy99.25 | 9 | 4d ago | |
| Twitter Misinformation Dataset | Unlearning Metric 117.7011 | 6 | 4d ago | ||
| Nudity (NSFW content) | MACE | CSDR12.9 | 6 | 4d ago | |
| VanGogh style | UCE | CSDR28.91 | 6 | 4d ago |
