RMU-unlearning detection on Yi-34B (test)
0.9993AccuracyUnlearning-trace detection classifier
Evaluation Results
| Method | Links | |
|---|---|---|
| Unlearning-trace detection classifierTraining source model=Yi-34B, Activation layer=pre-logit2025.06 | 0.9993 | |
| Unlearning-trace detection classifierTraining source model=Qwen2.5-14B, Activation layer=pre-logit2025.06 | 0.9896 | |
| Unlearning-trace detection classifierTraining source model=Zephyr-7B, Activation layer=pre-logit2025.06 | 0.9889 | |
| Unlearning-trace detection classifierTraining source model=Llama-3.1-8B, Activation layer=pre-logit2025.06 | 0.5243 |