Safety Alignment on MSSBench
79.18Safety ScoreSaFeR-ToolKit (+ SFT+DPO+GRPO) [3B]
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| SaFeR-ToolKit (+ SFT+DPO+GRPO) [3B]Model Scale=3B, Training Configuration=SFT+DPO+GRPO2026.03 | 79.18 | 72.55 | 75.2 | |
| SaFeR-ToolKit (+ SFT+DPO+GRPO) [7B]Model Scale=7B, Training Configuration=SFT+DPO+GRPO2026.03 | 79.18 | 84.69 | 83.06 | |
| Qwen2.5-VL-7BModel Scale=7B2026.03 | 25.41 | 37.55 | 6.73 | |
| Qwen2.5-VL-3BModel Scale=3B2026.03 | 11.33 | 34.08 | 0.71 |