Policy Violation Enforcement on MedAgentBench (Original)
0Unsafe Rate
Hong et al. (Manual Guardrails)
Updated 1mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| 0 | - | ||
| 23 | - | ||
| 39 | - | ||
| - | 30.3 | ||
| - | 57.7 | ||
| - | 55.7 |
Hong et al. (Manual Guardrails)
| Method | Links | ||
|---|---|---|---|
| 0 | - | ||
| 23 | - | ||
| 39 | - | ||
| - | 30.3 | ||
| - | 57.7 | ||
| - | 55.7 |