List your company

RMU-unlearning detection Zephyr-7B (test)

99.87AccuracyUnlearning-trace detection classifier
56.283667.599378.91590.2307Jun 16, 2025

Evaluation results

MethodLinks
Unlearning-trace detection classifierTraining source model=Zephyr-7B, Activation layer=pre-logit2025.0699.87
Unlearning-trace detection classifierTraining source model=Qwen2.5-14B, Activation layer=pre-logit2025.0695.45
Unlearning-trace detection classifierTraining source model=Yi-34B, Activation layer=pre-logit2025.0694.24
Unlearning-trace detection classifierTraining source model=Llama-3.1-8B, Activation layer=pre-logit2025.0657.96