Safety Content Detection on ToxiGen
72.3Detection Rategpt-oss-safeguard tailored policy
Evaluation results
| Method | Links | ||
|---|---|---|---|
| gpt-oss-safeguard tailored policyper-dataset tuning=false2026.06 | 72.3 | 3.5 |
| Method | Links | ||
|---|---|---|---|
| gpt-oss-safeguard tailored policyper-dataset tuning=false2026.06 | 72.3 | 3.5 |