Visual Question Answering on VQA v2 (Standard Accuracy)
78.53AccuracyLLaVA-1.5-7B
Evaluation results
| Method | Links | |
|---|---|---|
| LLaVA-1.5-7BFine-tuning Strategy=Full fine-tuning2025.03 | 78.53 | |
| RMU-UnlearningBase Model=LLaVA-1.5-13B, Fine-tuning Strategy=LoRA fine-tuning2025.03 | 78.27 | |
| NPO-UnlearningBase Model=LLaVA-1.5-7B, Fine-tuning Strategy=Full fine-tuning2025.03 | 77.34 |