List your company

Safety Evaluation on strongREJECT (Acceptance rate (%))

99.4Acceptance RateMisaligned LoRA
0.18425.94251.777.458Jun 8, 2026

Evaluation results

MethodLinks
Misaligned LoRAMitigation Strategy=w/o Mitigation2026.0699.4
Activation SteerMitigation Strategy=Realignment Methods, Training Free=true2026.0673.5
Gating InversionMitigation Strategy=Realignment Methods, Training Free=true2026.064.2
re-SFTMitigation Strategy=Realignment Methods, Training Free=false2026.064