Object Hallucination Evaluation on A-OKVQA POPE SEEM-annotated
91.6AccuracyDAMO
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| DAMOSetting=Random, Model=LLaVA1.5-13b2025.05 | 91.6 | 91.78 | |
| DCLASetting=Random, Model=LLaVA1.5-13b2025.05 | 91.5 | 91.28 | |
| DCLASetting=Random, Model=LLaVA-NEXT2025.05 | 91.1 | 90.69 | |
| RegularSetting=Random, Model=LLaVA-NEXT2025.05 | 91.07 | 90.87 | |
| RegularSetting=Random, Model=LLaVA1.5-13b2025.05 | 91.03 | 90.72 | |
| DAMOSetting=Random, Model=LLaVA-NEXT2025.05 | 90.87 | 90.43 | |
| DoLaSetting=Random, Model=LLaVA1.5-13b2025.05 | 90.77 | 90.37 | |
| DCLASetting=Popular, Model=LLaVA-NEXT2025.05 | 89.23 | 88.96 | |
| DCLASetting=Popular, Model=LLaVA1.5-13b2025.05 | 89.17 | 89.14 | |
| RegularSetting=Popular, Model=LLaVA-NEXT2025.05 | 89.13 | 88.87 | |
| RegularSetting=Popular, Model=LLaVA1.5-13b2025.05 | 89.13 | 88.97 | |
| DAMOSetting=Popular, Model=LLaVA1.5-13b2025.05 | 89.07 | 89.56 | |
| DAMOSetting=Popular, Model=LLaVA-NEXT2025.05 | 89.03 | 88.72 | |
| VCDSetting=Random, Model=LLaVA1.5-13b2025.05 | 89 | 88.33 | |
| DoLaSetting=Popular, Model=LLaVA1.5-13b2025.05 | 88.93 | 88.68 | |
| DoLaSetting=Random, Model=LLaVA-NEXT2025.05 | 88.73 | 87.68 | |
| DAMOSetting=Random, Model=mPLUG-Owl22025.05 | 88.26 | 88.43 | |
| DCLASetting=Random, Model=mPLUG-Owl22025.05 | 88.1 | 88.16 | |
| RegularSetting=Random, Model=mPLUG-Owl22025.05 | 88.09 | 88.17 | |
| DCLASetting=Random, Model=LLaVA1.5-7b2025.05 | 87.93 | 88.98 | |
| DAMOSetting=Random, Model=LLaVA1.5-7b2025.05 | 87.83 | 88.88 | |
| DoLaSetting=Popular, Model=LLaVA-NEXT2025.05 | 87.83 | 86.83 | |
| DoLaSetting=Random, Model=mPLUG-Owl22025.05 | 87.63 | 86.96 | |
| RegularSetting=Random, Model=LLaVA1.5-7b2025.05 | 87.23 | 88.44 | |
| VCDSetting=Popular, Model=LLaVA1.5-13b2025.05 | 86.73 | 86.26 | |
| VCDSetting=Random, Model=LLaVA1.5-7b2025.05 | 86.37 | 87.44 | |
| DoLaSetting=Random, Model=LLaVA1.5-7b2025.05 | 86.1 | 87.48 | |
| DoLaSetting=Popular, Model=mPLUG-Owl22025.05 | 84.47 | 84.15 | |
| DCLASetting=Popular, Model=mPLUG-Owl22025.05 | 84.43 | 85.06 | |
| RegularSetting=Popular, Model=mPLUG-Owl22025.05 | 84.33 | 84.18 | |
| DAMOSetting=Popular, Model=mPLUG-Owl22025.05 | 84.07 | 84.92 | |
| DAMOSetting=Adversarial, Model=LLaVA-NEXT2025.05 | 83.16 | 83.68 | |
| VCDSetting=Random, Model=mPLUG-Owl22025.05 | 82.83 | 81.49 | |
| DoLaSetting=Adversarial, Model=LLaVA-NEXT2025.05 | 82.83 | 82.37 | |
| DCLASetting=Adversarial, Model=LLaVA-NEXT2025.05 | 82.33 | 83.08 | |
| DoLaSetting=Adversarial, Model=LLaVA1.5-13b2025.05 | 82.07 | 82.86 | |
| DCLASetting=Adversarial, Model=LLaVA1.5-13b2025.05 | 82.07 | 83.22 | |
| RegularSetting=Adversarial, Model=LLaVA-NEXT2025.05 | 82.03 | 82.85 | |
| RegularSetting=Adversarial, Model=LLaVA1.5-13b2025.05 | 81.93 | 82.91 | |
| VCDSetting=Random, Model=LLaVA-NEXT2025.05 | 81.13 | 77.45 | |
| DCLASetting=Popular, Model=LLaVA1.5-7b2025.05 | 81.13 | 83.78 | |
| DAMOSetting=Adversarial, Model=LLaVA1.5-13b2025.05 | 81.13 | 83.25 | |
| DAMOSetting=Popular, Model=LLaVA1.5-7b2025.05 | 81.07 | 83.7 | |
| VCDSetting=Popular, Model=LLaVA-NEXT2025.05 | 80.9 | 77.23 | |
| VCDSetting=Popular, Model=mPLUG-Owl22025.05 | 80.77 | 79.93 | |
| DoLaSetting=Popular, Model=LLaVA1.5-7b2025.05 | 80.4 | 83.21 | |
| VCDSetting=Adversarial, Model=LLaVA1.5-13b2025.05 | 80.4 | 80.95 | |
| RegularSetting=Popular, Model=LLaVA1.5-7b2025.05 | 80.1 | 83.07 | |
| VCDSetting=Popular, Model=LLaVA1.5-7b2025.05 | 78.9 | 81.82 | |
| DoLaSetting=Adversarial, Model=mPLUG-Owl22025.05 | 78.17 | 79.14 | |
| DCLASetting=Adversarial, Model=mPLUG-Owl22025.05 | 77.07 | 79.44 | |
| RegularSetting=Adversarial, Model=mPLUG-Owl22025.05 | 76.67 | 78.71 | |
| DAMOSetting=Adversarial, Model=mPLUG-Owl22025.05 | 76.2 | 79.04 | |
| VCDSetting=Adversarial, Model=LLaVA-NEXT2025.05 | 75.7 | 72.72 | |
| VCDSetting=Adversarial, Model=mPLUG-Owl22025.05 | 73.5 | 74.26 | |
| DAMOSetting=Adversarial, Model=LLaVA1.5-7b2025.05 | 70.64 | 76.85 | |
| DCLASetting=Adversarial, Model=LLaVA1.5-7b2025.05 | 70.23 | 76.6 | |
| DoLaSetting=Adversarial, Model=LLaVA1.5-7b2025.05 | 69.6 | 76.16 | |
| RegularSetting=Adversarial, Model=LLaVA1.5-7b2025.05 | 69.2 | 76.02 | |
| VCDSetting=Adversarial, Model=LLaVA1.5-7b2025.05 | 68.3 | 74.97 |