Harmful Question Forgetting on Harm-1 GPTFUZZER WildAttack
61ASRRetainOnlyFT
Evaluation results
| Method | Links | |
|---|---|---|
| RetainOnlyFTModel=Llama-3.2-1B-Instruct2026.04 | 61 | |
| RetainOnlyFTModel=OLMo-2-1B-Instruct2026.04 | 31 | |
| Llama-3.2-1B-InstructModel=Llama-3.2-1B-Instruct2026.04 | 7 | |
| RetainOnlyFTModel=OLMo-2-7B-Instruct2026.04 | 4 | |
| DPOModel=Llama-3.2-1B-Instruct2026.04 | 3 | |
| SKUModel=Llama-3.2-1B-Instruct2026.04 | 3 | |
| DPOModel=Llama-3.2-3B-Instruct2026.04 | 3 | |
| Llama-3.2-3B-InstructModel=Llama-3.2-3B-Instruct2026.04 | 2 | |
| DPOModel=OLMo-2-1B-Instruct2026.04 | 2 | |
| OLMo-2-1B-InstructModel=OLMo-2-1B-Instruct2026.04 | 1 | |
| EraserModel=OLMo-2-1B-Instruct, Hyperparameter (λ)=0.62026.04 | 1 | |
| UnlearningModel=Llama-3.2-1B-Instruct, Hyperparameter (λ)=0.62026.04 | 0 | |
| EraserModel=Llama-3.2-1B-Instruct, Hyperparameter (λ)=0.62026.04 | 0 | |
| EUModel=Llama-3.2-1B-Instruct, Hyperparameter (λ)=0.62026.04 | 0 | |
| RetainOnlyFTModel=Llama-3.2-3B-Instruct2026.04 | 0 | |
| UnlearningModel=Llama-3.2-3B-Instruct, Hyperparameter (λ)=0.62026.04 | 0 | |
| EraserModel=Llama-3.2-3B-Instruct, Hyperparameter (λ)=0.62026.04 | 0 | |
| SKUModel=Llama-3.2-3B-Instruct2026.04 | 0 | |
| EUModel=Llama-3.2-3B-Instruct, Hyperparameter (λ)=0.62026.04 | 0 | |
| UnlearningModel=OLMo-2-1B-Instruct, Hyperparameter (λ)=0.62026.04 | 0 | |
| SKUModel=OLMo-2-1B-Instruct2026.04 | 0 | |
| EUModel=OLMo-2-1B-Instruct, Hyperparameter (λ)=0.62026.04 | 0 | |
| OLMo-2-7B-InstructModel=OLMo-2-7B-Instruct2026.04 | 0 | |
| DPOModel=OLMo-2-7B-Instruct2026.04 | 0 | |
| UnlearningModel=OLMo-2-7B-Instruct, Hyperparameter (λ)=0.62026.04 | 0 | |
| EraserModel=OLMo-2-7B-Instruct, Hyperparameter (λ)=0.62026.04 | 0 | |
| SKUModel=OLMo-2-7B-Instruct2026.04 | 0 | |
| EUModel=OLMo-2-7B-Instruct, Hyperparameter (λ)=0.62026.04 | 0 |