Benign Prompt Classification on Just-Eval benign
99AccuracyPR
Evaluation Results
| Method | Links | |
|---|---|---|
| PRTarget Model=Phi-32026.05 | 99 | |
| PTarget Model=Llama-32026.05 | 98 | |
| PRTarget Model=Llama-32026.05 | 98 | |
| Y(O)Target Model=Llama-32026.05 | 98 | |
| Y(S)Target Model=Llama-32026.05 | 98 | |
| PTarget Model=Qwen-1.52026.05 | 98 | |
| PRTarget Model=Qwen-1.52026.05 | 98 | |
| Y(O)Target Model=Qwen-1.52026.05 | 98 | |
| Y(S)Target Model=Qwen-1.52026.05 | 98 | |
| PTarget Model=Phi-32026.05 | 98 | |
| Y(O)Target Model=Phi-32026.05 | 98 | |
| Y(S)Target Model=Phi-32026.05 | 98 | |
| PPLTarget Model=Llama-32026.05 | 88 | |
| PPLTarget Model=Qwen-1.52026.05 | 88 | |
| PPLTarget Model=Phi-32026.05 | 88 |