Policy Violation Enforcement on MedAgentBench (Adversarial)
0Unsafe Rate (Hong et al.)
Hong et al. (Manual Guardrails)
Updated 1mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| 0 | - | ||
| 62 | - | ||
| 78 | - | ||
| - | 72 | ||
| - | 82 | ||
| - | 85.7 |
Hong et al. (Manual Guardrails)
| Method | Links | ||
|---|---|---|---|
| 0 | - | ||
| 62 | - | ||
| 78 | - | ||
| - | 72 | ||
| - | 82 | ||
| - | 85.7 |