List your company

Jailbreak Defense on Hard (H)

0FPRTRLM-Ba
-0.683.918.513.09Dec 3, 2024

Evaluation results

MethodLinks
TRLM-BaThresh=2, Training Protocol=Pretrained (PT)2024.120
TRLM-BaThresh=4, Training Protocol=Pretrained (PT)2024.120
TRLM-BaThresh=6, Training Protocol=Pretrained (PT)2024.120
TRLM-BaThresh=2, Training Protocol=Instruction-finetuned (IT)2024.120
TRLM-BaThresh=4, Training Protocol=Instruction-finetuned (IT)2024.120
TRLM-BaThresh=6, Training Protocol=Instruction-finetuned (IT)2024.120
TRLM-FOThresh=4, Training Protocol=Instruction-finetuned (IT)2024.121
TRLM-FOThresh=6, Training Protocol=Instruction-finetuned (IT)2024.121
TRLM-FOThresh=2, Training Protocol=Instruction-finetuned (IT)2024.123
TRLM-FOThresh=6, Training Protocol=Pretrained (PT)2024.126
TRLM-FOThresh=4, Training Protocol=Pretrained (PT)2024.1212
TRLM-FOThresh=2, Training Protocol=Pretrained (PT)2024.1217