Hallucination Detection on VQA-RAD Open-Ended
70AUC
V-Loop
Updated 4d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.01 | 70 | 56.47 | |
2026.01 | 68.2 | 57.68 | |
2026.01 | 67.06 | 55.91 | |
2026.01 | 66.32 | 66.51 | |
2026.01 | 63.5 | 60.17 | |
2026.01 | 63.33 | 63.03 | |
2026.01 | 62.91 | 62.87 | |
2026.01 | 62.8 | 60.17 | |
2026.01 | 61.26 | 53.89 | |
2026.01 | 61.17 | 52.11 | |
2026.01 | 58.89 | 51.44 | |
2026.01 | 52.4 | 49.64 | |
2026.01 | 51.9 | 48.35 | |
2026.01 | 50.52 | 47.85 | |
2026.01 | 50.37 | 47.69 | |
2026.01 | 49.63 | 47.13 | |
2026.01 | 49.48 | 47.07 | |
2026.01 | 39.88 | 42.12 | |
2026.01 | 38.4 | 38.05 | |
2026.01 | 36.86 | 45.37 | |
2026.01 | 36.36 | 43.47 |