Semantic Alignment on Safety Concepts Famous Celebrities
-0.0601Delta OriginalUndefended Model
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| Undefended Model2026.02 | -0.0601 | — | — | — | |
| ReVision2026.02 | — | 0.1534 | 0.2135 | 0.1153 |
| Method | Links | ||||
|---|---|---|---|---|---|
| Undefended Model2026.02 | -0.0601 | — | — | — | |
| ReVision2026.02 | — | 0.1534 | 0.2135 | 0.1153 |