Domain-specific Question Answering on psychol
2.75Relative Accuracy ImprovementLWF
Evaluation results
| Method | Links | ||
|---|---|---|---|
| LWFModel=Llama3-8B, Unlearning Target=sst52025.05 | 2.75 | — | |
| LWFModel=Llama3-8B, Unlearning Target=gsm8k2025.05 | 2.06 | — | |
| LWFModel=Llama3-8B, Unlearning Target=mixed2025.05 | 1.6 | — | |
| LWFModel=Llama3-8B, Unlearning Target=dental2025.05 | 0.91 | — | |
| LWFModel=Llama3-8B, Unlearning Target=qasc2025.05 | 0.46 | — | |
| Vanilla Fine-tuningModel=Llama3-8B, Unlearning Target=none2025.05 | — | 80 |