Hallucination Detection on COCO-Caption (val)
77.11A-ROC
RepProbing
Updated 4d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.01 | 77.11 | 66.14 | |
2026.01 | 76.83 | 70.52 | |
2026.01 | 75.24 | 66.51 | |
2026.01 | 75.16 | 69.32 | |
2026.01 | 74.95 | 67.29 | |
2026.01 | 74.2 | 68.17 | |
2026.01 | 74.14 | 67.64 | |
2026.01 | 74.06 | 64.99 | |
2026.01 | 72.98 | 64.73 | |
2026.01 | 72.55 | 62.82 | |
2026.01 | 72.33 | 62.56 | |
2026.01 | 71.92 | 64.99 | |
2026.01 | 71.83 | 62.64 | |
2026.01 | 70.89 | 61.2 | |
2026.01 | 69.52 | 58.13 | |
2026.01 | 67.78 | 58.55 | |
2026.01 | 67.28 | 58.3 | |
2026.01 | 67.23 | 59.35 | |
2026.01 | 65.96 | 56.88 | |
2026.01 | 65.7 | 55.34 | |
2026.01 | 60.21 | 35.26 | |
2026.01 | 59.05 | 34.18 | |
2026.01 | 58.93 | 32.01 | |
2026.01 | 58.88 | 36.95 | |
2026.01 | 56.94 | 34.43 | |
2026.01 | 56.78 | 33.2 | |
2026.01 | 55.89 | 34.72 | |
2026.01 | 55.36 | 32.67 | |
2026.01 | 54.45 | 33.92 | |
2026.01 | 52.08 | 30.81 |