Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Hallucination Detection on VQA-Med Open-Ended 2019

72.86AUC

V-Loop

34.983244.816654.6564.4834Jan 26, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.01
72.8656.58
2026.01
71.9366.33
2026.01
67.6953.58
2026.01
66.1852.19
2026.01
66.0250.92
2026.01
64.9136.42
2026.01
63.8146.94
2026.01
61.8847.02
2026.01
60.4642.05
2026.01
58.5833.58
2026.01
56.9432.85
2026.01
55.2440.67
2026.01
54.1340
2026.01
54.0739.98
2026.01
51.839.39
2026.01
45.9346.15
2026.01
45.8744.81
2026.01
42.9635.43
2026.01
41.2830
2026.01
38.8933.64
2026.01
36.4428.27