List your company

Hallucination Detection on VQA-Med Open-Ended 2019

78.65AUCVIHD
34.751646.148357.54568.9417Jan 26, 2026Feb 14, 2026Mar 5, 2026Mar 24, 2026Apr 12, 2026May 1, 2026May 20, 2026

Evaluation results

MethodLinks
VIHDBackbone=Hulu-4B2026.0578.6559.64
VASEBackbone=Hulu-4B2026.0575.0954.3
VIHDBackbone=Lingshu-7B2026.0574.7164.11
V-LoopBackbone=InternVL3-8B2026.0172.8656.58
V-LoopBackbone=Lingshu-7B2026.0171.9366.33
MaxEntBackbone=Hulu-4B2026.0571.6752.74
MaxProbBackbone=Hulu-4B2026.0571.4551.86
AvgProbBackbone=Hulu-4B2026.0570.4851.56
AvgEntBackbone=Hulu-4B2026.0570.4351.68
VASEBackbone=Lingshu-7B2026.0569.5756.77
RadFlagBackbone=InternVL3-8B, Uncertainty-based=true2026.0167.6953.58
SEBackbone=InternVL3-8B, Uncertainty-based=true2026.0166.1852.19
V-LoopBackbone=MedGemma-4B-it2026.0166.0250.92
RadFlagBackbone=MedGemma-4B-it, Uncertainty-based=true2026.0164.9136.42
MaxEntBackbone=InternVL3-8B2026.0163.8146.94
SEBackbone=MedGemma-4B-it, Uncertainty-based=true2026.0161.8847.02
AvgEntBackbone=InternVL3-8B2026.0160.4642.05
MaxEntBackbone=MedGemma-4B-it2026.0158.5833.58
RadFlagBackbone=Lingshu-7B2026.0557.335.91
AvgEntBackbone=MedGemma-4B-it2026.0156.9432.85
AvgEntBackbone=Lingshu-7B2026.0555.6835.63
MaxEntBackbone=Lingshu-7B2026.0555.6435.59
AvgProbBackbone=Lingshu-7B2026.0555.6135.54
MaxProbBackbone=Lingshu-7B2026.0555.5935.54
RadFlagBackbone=Lingshu-7B, Uncertainty-based=true2026.0155.2440.67
SEBackbone=Lingshu-7B2026.0554.2734.69
MaxEntBackbone=Lingshu-7B2026.0154.1340
AvgEntBackbone=Lingshu-7B2026.0154.0739.98
SEBackbone=Lingshu-7B, Uncertainty-based=true2026.0151.839.39
RadFlagBackbone=Hulu-4B2026.055021.74
SEBackbone=Hulu-4B2026.0547.5319.58
AvgProbBackbone=Lingshu-7B2026.0145.9346.15
MaxProbBackbone=Lingshu-7B2026.0145.8744.81
AvgProbBackbone=MedGemma-4B-it2026.0142.9635.43
MaxProbBackbone=MedGemma-4B-it2026.0141.2830
AvgProbBackbone=InternVL3-8B2026.0138.8933.64
MaxProbBackbone=InternVL3-8B2026.0136.4428.27