Jailbreak Defense on Easy (E)
0FPRTRLM-FO
Evaluation Results
| Method | Links | |
|---|---|---|
| TRLM-FOThresh=4, Training Protocol=Pretrained (PT)2024.12 | 0 | |
| TRLM-FOThresh=6, Training Protocol=Pretrained (PT)2024.12 | 0 | |
| TRLM-FOThresh=2, Training Protocol=Instruction-finetuned (IT)2024.12 | 0 | |
| TRLM-FOThresh=4, Training Protocol=Instruction-finetuned (IT)2024.12 | 0 | |
| TRLM-FOThresh=6, Training Protocol=Instruction-finetuned (IT)2024.12 | 0 | |
| TRLM-FOThresh=2, Training Protocol=Pretrained (PT)2024.12 | 2 | |
| TRLM-BaThresh=4, Training Protocol=Pretrained (PT)2024.12 | 2 | |
| TRLM-BaThresh=6, Training Protocol=Pretrained (PT)2024.12 | 2 | |
| TRLM-BaThresh=6, Training Protocol=Instruction-finetuned (IT)2024.12 | 2 | |
| TRLM-BaThresh=4, Training Protocol=Instruction-finetuned (IT)2024.12 | 4 | |
| TRLM-BaThresh=2, Training Protocol=Pretrained (PT)2024.12 | 8 | |
| TRLM-BaThresh=2, Training Protocol=Instruction-finetuned (IT)2024.12 | 8 |