Harmful Request Compliance on Harmful Requests TAP-T
85.8Compliance RateMistral-7B-Instruct-v2
Evaluation Results
| Method | Links | |
|---|---|---|
| Mistral-7B-Instruct-v2Base Model=Mistral-7B-Instruct-v2, Training Configuration=Refusal Trained2024.06 | 85.8 | |
| R2D2Base Model=Mistral-7B-Instruct-v2, Training Configuration=Adv Trained2024.06 | 68.7 | |
| Representation ReroutingBase Model=Mistral-7B-Instruct-v2, Training Configuration=+ RR2024.06 | 17.5 | |
| Llama-3-8B-InstructBase Model=Llama-3-8B-Instruct, Training Configuration=Refusal Trained2024.06 | 17.4 | |
| Representation ReroutingBase Model=Llama-3-8B-Instruct, Training Configuration=+ RR2024.06 | 2.1 | |
| CygnetBase Model=Llama-3-8B-Instruct, Training Configuration=Circuit Breaker + RepE Fine-tune2024.06 | 0 |