Object Hallucination Detection on POPE (average over three sampling strategies)
83.94AUROC
InsLen
Updated 21d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.05 | 83.94 | 96.14 | |
2026.05 | 79.42 | 96.45 | |
2026.05 | 76.5 | 95.9 | |
2026.05 | 75.42 | 93.7 | |
2026.05 | 74.09 | 94.59 | |
2026.05 | 73.52 | 92.89 | |
2026.05 | 70.13 | 87.32 | |
2026.05 | 68.43 | 92.27 | |
2026.05 | 68.38 | 89.4 | |
2026.05 | 68.24 | 88.44 | |
2026.05 | 67.16 | 90.02 | |
2026.05 | 64.26 | 88.84 | |
2026.05 | 63.74 | 86.01 | |
2026.05 | 63.62 | 85 | |
2026.05 | 61.47 | 88.23 | |
2026.05 | 61.42 | 86.97 | |
2026.05 | 60.73 | 84.69 | |
2026.05 | 60.6 | 87.89 | |
2026.05 | 59.51 | 88.46 | |
2026.05 | 58.2 | 88.46 | |
2026.05 | 58.07 | 87.18 | |
2026.05 | 56.07 | 83.94 | |
2026.05 | 55.46 | 89.63 | |
2026.05 | 55.35 | 87.35 | |
2026.05 | 55.19 | 92.59 | |
2026.05 | 54.65 | 87.55 | |
2026.05 | 54.41 | 85.87 | |
2026.05 | 54.25 | 87.35 | |
2026.05 | 53.46 | 83.17 | |
2026.05 | 53.2 | 86.64 | |
2026.05 | 52.59 | 85.66 | |
2026.05 | 52 | 81.77 | |
2026.05 | 51.62 | 85.21 | |
2026.05 | 46.64 | 86.75 | |
2026.05 | 46.39 | 87.54 |