Object Hallucination Detection on MME existence
98.33AccuracyR-CoV
Evaluation results
| Method | Links | ||
|---|---|---|---|
| R-CoVModel=LLaVA-1.52026.04 | 98.33 | 96.67 | |
| R-CoVModel=Qwen2.5-VL2026.04 | 98.33 | 96.67 | |
| R-CoVModel=mPLUG-Owl2026.04 | 96.67 | 93.33 | |
| VanillaModel=LLaVA-1.52026.04 | 96.67 | 93.33 | |
| SelfCheckModel=LLaVA-1.52026.04 | 96.67 | 93.33 | |
| LogicCheckGPTModel=LLaVA-1.52026.04 | 96.67 | 93.33 | |
| LogicCheckGPTModel=mPLUG-Owl2026.04 | 95 | 90 | |
| VanillaModel=Qwen2.5-VL2026.04 | 95 | 90 | |
| LogicCheckGPTModel=Qwen2.5-VL2026.04 | 95 | 90 | |
| LUREModel=LLaVA-1.52026.04 | 93.33 | 86.67 | |
| R-CoVModel=MiniGPT-42026.04 | 88.33 | 76.67 | |
| LogicCheckGPTModel=MiniGPT-42026.04 | 86.67 | 73.33 | |
| SelfCheckModel=mPLUG-Owl2026.04 | 85 | 73.33 | |
| LUREModel=MiniGPT-42026.04 | 85 | 70 | |
| LRV-InstructionModel=mPLUG-Owl2026.04 | 83.33 | 66.67 | |
| LRV-InstructionModel=MiniGPT-42026.04 | 83.33 | 66.67 | |
| LUREModel=mPLUG-Owl2026.04 | 80 | 60 | |
| SelfCheckModel=MiniGPT-42026.04 | 80 | 60 | |
| VanillaModel=MiniGPT-42026.04 | 78.33 | 56.67 | |
| VanillaModel=mPLUG-Owl2026.04 | 65 | 35 |