Hallucination Detection on VQA-RAD (All)
63.99AUC
RadFlag
Updated 4d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.01 | 63.99 | 57.98 | |
2026.01 | 61.59 | 57.14 | |
2026.01 | 60.98 | 58.15 | |
2026.01 | 60.3 | 66.91 | |
2026.01 | 60.04 | 56.01 | |
2026.01 | 59.67 | 54.34 | |
2026.01 | 58.69 | 57.94 | |
2026.01 | 56.65 | 59.76 | |
2026.01 | 56.11 | 58.97 | |
2026.01 | 55.6 | 58.33 | |
2026.01 | 51.76 | 60.96 | |
2026.01 | 51.73 | 60.96 | |
2026.01 | 51.55 | 59.29 | |
2026.01 | 50.96 | 59.16 | |
2026.01 | 50.04 | 62.84 | |
2026.01 | 48.27 | 56.36 | |
2026.01 | 48.24 | 55.44 | |
2026.01 | 44.49 | 54.25 | |
2026.01 | 43.71 | 53.12 | |
2026.01 | 39.77 | 43.33 | |
2026.01 | 38.66 | 40.72 |