LLM Jailbreaking on Mistral CB
72Success Rate First (SRF)
Adaptive Probe-based Steering
Updated 13d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| 72 | 81 | 95 | ||
2026.05 | 2 | 2 | 0 | |
2026.05 | 2 | 2 | 1 | |
2026.05 | 1 | 0 | 1 |
Adaptive Probe-based Steering
| Method | Links | |||
|---|---|---|---|---|
| 72 | 81 | 95 | ||
2026.05 | 2 | 2 | 0 | |
2026.05 | 2 | 2 | 1 | |
2026.05 | 1 | 0 | 1 |