BeaverTails, ToxicChat, PKU-SafeRLHF
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Harmfulness detection | BeaverTails, ToxicChat, PKU-SafeRLHF Hard (test) | AUROC90.2 | 63 |
Showing 1 of 1 rows
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Harmfulness detection | BeaverTails, ToxicChat, PKU-SafeRLHF Hard (test) | AUROC90.2 | 63 |