Refusal Evaluation on Past Tense
51ASRQwen2.5-7B-Instruct
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen2.5-7B-InstructBase Model=Qwen2.5-7B-Instruct2025.09 | 51 | |
| DPOBase Model=Qwen2.5-7B-Instruct2025.09 | 49 | |
| SFT (5/95)Base Model=Qwen2.5-7B-Instruct2025.09 | 47 | |
| CBBase Model=Qwen2.5-7B-Instruct2025.09 | 47 | |
| RepEBase Model=Qwen2.5-7B-Instruct2025.09 | 46 | |
| Llama-3.1-8B-InstructBase Model=Llama-3.1-8B-Instruct2025.09 | 42 | |
| RepEBase Model=Llama-3.1-8B-Instruct2025.09 | 41 | |
| Head AblationBase Model=Qwen2.5-7B-Instruct2025.09 | 41 | |
| DPOBase Model=Llama-3.1-8B-Instruct2025.09 | 38 | |
| Gemma-2-9B-itBase Model=Gemma-2-9B-it2025.09 | 38 | |
| Only ScalingBase Model=Qwen2.5-7B-Instruct2025.09 | 37 | |
| DPOBase Model=Gemma-2-9B-it2025.09 | 37 | |
| CBBase Model=Gemma-2-9B-it2025.09 | 36 | |
| Head AblationBase Model=Gemma-2-9B-it2025.09 | 34 | |
| RepEBase Model=Gemma-2-9B-it2025.09 | 34 | |
| RepBendBase Model=Qwen2.5-7B-Instruct2025.09 | 30 | |
| Head AblationBase Model=Llama-3.1-8B-Instruct2025.09 | 29 | |
| OLMo-2-1124-7B-InstructBase Model=OLMo-2-1124-7B-Instruct2025.09 | 28 | |
| RepBendBase Model=Gemma-2-9B-it2025.09 | 27 | |
| Only ScalingBase Model=Gemma-2-9B-it2025.09 | 26 | |
| DPOBase Model=OLMo-2-1124-7B-Instruct2025.09 | 25 | |
| RepBendBase Model=OLMo-2-1124-7B-Instruct2025.09 | 23 | |
| Head AblationBase Model=OLMo-2-1124-7B-Instruct2025.09 | 22 | |
| RepEBase Model=OLMo-2-1124-7B-Instruct2025.09 | 22 | |
| SFT (5/95)Base Model=Llama-3.1-8B-Instruct2025.09 | 21 | |
| SFT (5/95)Base Model=OLMo-2-1124-7B-Instruct2025.09 | 21 | |
| CBBase Model=OLMo-2-1124-7B-Instruct2025.09 | 20 | |
| ASGUARDBase Model=Gemma-2-9B-it2025.09 | 19 | |
| Only ScalingBase Model=OLMo-2-1124-7B-Instruct2025.09 | 17 | |
| Only ScalingBase Model=Llama-3.1-8B-Instruct2025.09 | 13 | |
| RepBendBase Model=Llama-3.1-8B-Instruct2025.09 | 11 | |
| ASGUARDBase Model=OLMo-2-1124-7B-Instruct2025.09 | 9 | |
| ASGUARDBase Model=Llama-3.1-8B-Instruct2025.09 | 8 | |
| ASGUARDBase Model=Qwen2.5-7B-Instruct2025.09 | 8 | |
| SFT (30/70)Base Model=OLMo-2-1124-7B-Instruct2025.09 | 8 | |
| SFT (30/70)Base Model=Llama-3.1-8B-Instruct2025.09 | 3 | |
| CBBase Model=Llama-3.1-8B-Instruct2025.09 | 0 | |
| SFT (30/70)Base Model=Qwen2.5-7B-Instruct2025.09 | 0 | |
| SFT (5/95)Base Model=Gemma-2-9B-it2025.09 | 0 | |
| SFT (30/70)Base Model=Gemma-2-9B-it2025.09 | 0 |