Safety Assessment on Safety Prompts (randomly selected 200 samples per field)
1.5Insensitivity Score
llama2 -> CP -> FT + 0.5 chat vector
Updated 4d ago
Evaluation Results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| 1.5 | 0 | 0.5 | 0.5 | 0 | 0.5 | 0 | ||
| 2 | 0.5 | 1 | 0.5 | 0 | 0 | 0 | ||
2023.10 | 2.5 | 0 | 0.5 | 0.5 | 0 | 1 | 0.5 | |
2023.10 | 5 | 2 | 3 | 1 | 0 | 1 | 0 | |
| 7.5 | 4 | 2.5 | 2 | 0 | 6 | 1.5 | ||
2023.10 | 13 | 11.5 | 14.5 | 2.5 | 0 | 11 | 2.5 | |
2023.10 | 13.5 | 3 | 8 | 5.5 | 1.5 | 6.5 | 5 | |
| 47.5 | 28.5 | 17 | 1 | 6 | 4.5 | 9 | ||
2023.10 | 66 | 24 | 37.5 | 1.5 | 1 | 15.5 | 4 |