Safety Evaluation on DangerousQA (test)
0.0122Harmful RateAdvBench-R2J Alignment
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| AdvBench-R2J AlignmentAlignment Dataset=AdvBench-R2J2025.02 | 0.0122 | 0.135 | |
| AdvBench AlignmentAlignment Dataset=AdvBench2025.02 | 0.0134 | 0.19 | |
| w/o SFTAlignment Dataset=None2025.02 | 0.0334 | 0.58 |