ALERT
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Prohibited Content Detection | ALERT | ASR15 | 34 | |
| Safety Evaluation | ALERT (test) | ASR0.2 | 7 | |
| Malicious Prompt Detection | Babelscape ALERT | Accuracy99.73 | 4 | |
| General Safety / Red-Teaming | ALERT | Metric- | 0 |
Showing 4 of 4 rows