Out-of-Taxonomy Risk Detection on BeaverTails V
0.6314F1 ScoreProGuard-7B
Evaluation Results
| Method | Links | |
|---|---|---|
| ProGuard-7B2025.12 | 0.6314 | |
| GPT4o-mini2025.12 | 0.5107 | |
| ProGuard-3B2025.12 | 0.4586 | |
| Gemini2.5-Flash2025.12 | 0.4316 |
Loading the SOTA2 catalog…
| Method | Links | |
|---|---|---|
| ProGuard-7B2025.12 | 0.6314 | |
| GPT4o-mini2025.12 | 0.5107 | |
| ProGuard-3B2025.12 | 0.4586 | |
| Gemini2.5-Flash2025.12 | 0.4316 |