Content Safety Detection on PhishBots
98.1F1 Scoreprompt–response verification framework
Evaluation results
| Method | Links | ||
|---|---|---|---|
| prompt–response verification framework2026.06 | 98.1 | 1.9 | |
| ScamLLMType=Strongest Applicable Baseline2026.06 | 95.8 | — |
| Method | Links | ||
|---|---|---|---|
| prompt–response verification framework2026.06 | 98.1 | 1.9 | |
| ScamLLMType=Strongest Applicable Baseline2026.06 | 95.8 | — |