Keyword Prediction on GCG jailbreaking prompts (test)
66.4Precision
EnsembleSHAP
Updated 3mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.03 | 66.4 | 58.4 | |
2026.03 | 65.4 | 57.5 | |
2026.03 | 65.1 | 57.1 | |
2026.03 | 54.4 | 46.6 |
EnsembleSHAP
| Method | Links | ||
|---|---|---|---|
2026.03 | 66.4 | 58.4 | |
2026.03 | 65.4 | 57.5 | |
2026.03 | 65.1 | 57.1 | |
2026.03 | 54.4 | 46.6 |