Object Hallucination Evaluation on OPOPE
80.05AccuracyCIPHER
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| CIPHERBase Model=LLaVA-1.52026.03 | 80.05 | 93.72 | 92.11 | |
| NulluBase Model=LLaVA-1.52026.03 | 79.52 | 93.46 | 91.79 | |
| Beam SearchBase Model=LLaVA-1.52026.03 | 79.41 | 92.52 | 90.96 | |
| OPERABase Model=LLaVA-1.52026.03 | 79.29 | 92.25 | 90.71 | |
| GreedyBase Model=LLaVA-1.52026.03 | 79.14 | 91.98 | 90.45 | |
| DoLaBase Model=LLaVA-1.52026.03 | 78.98 | 91.66 | 90.15 | |
| VCDBase Model=LLaVA-1.52026.03 | 78.01 | 91.33 | 89.69 | |
| HALCBase Model=LLaVA-1.52026.03 | 77.87 | 93.17 | 91.25 | |
| CIPHERBase Model=mPLUG-Owl22026.03 | 77.87 | 92.93 | 90.95 | |
| NulluBase Model=mPLUG-Owl22026.03 | 77.09 | 92.83 | 90.8 | |
| Beam SearchBase Model=mPLUG-Owl22026.03 | 76.76 | 90.28 | 88.56 | |
| GreedyBase Model=mPLUG-Owl22026.03 | 76.46 | 88.85 | 87.29 | |
| DoLaBase Model=mPLUG-Owl22026.03 | 76.07 | 88.54 | 86.95 | |
| OPERABase Model=mPLUG-Owl22026.03 | 75.49 | 91.23 | 89.11 | |
| VCDBase Model=mPLUG-Owl22026.03 | 75.49 | 88.75 | 87.02 | |
| HALCBase Model=mPLUG-Owl22026.03 | 74.93 | 90.2 | 88.12 | |
| CIPHERBase Model=MiniGPT-42026.03 | 72.25 | 96.5 | 92.58 | |
| NulluBase Model=MiniGPT-42026.03 | 71.92 | 95.96 | 92.07 | |
| Beam SearchBase Model=MiniGPT-42026.03 | 71.65 | 94.7 | 90.97 | |
| DoLaBase Model=MiniGPT-42026.03 | 71.28 | 93.92 | 90.22 | |
| GreedyBase Model=MiniGPT-42026.03 | 71.22 | 93.72 | 90.04 | |
| HALCBase Model=MiniGPT-42026.03 | 71.17 | 94.88 | 90.95 | |
| VCDBase Model=MiniGPT-42026.03 | 70.83 | 92.31 | 88.76 | |
| OPERABase Model=MiniGPT-42026.03 | 70.48 | 94.41 | 90.66 |