| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Memorization Reduction | Ultrachat | Memorization Reduction95.7 | 20 | |
| Unlearning Detection | UltraChat | Accuracy99.86 | 12 | |
| Natural Language Generation | UltraChat | BLEU36.8 | 8 | |
| Conversational Instruction Following | UltraChat | Overall Score9.1 | 6 | |
| Personalized Interaction | ultrachat Synthetic | Personalization Score7.26 | 6 | |
| Unlearning detection (distinguishing original vs. RMU-unlearned) | UltraChat (test) | Accuracy0.8746 | 4 |