Salad
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Refusal Steering | SALAD Alpaca HarmBench | Target Success99.8 | 18 | |
| Adversarial Attack Detection | Salad-Data | Recall96 | 15 |
Showing 2 of 2 rows
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Refusal Steering | SALAD Alpaca HarmBench | Target Success99.8 | 18 | |
| Adversarial Attack Detection | Salad-Data | Recall96 | 15 |