List your company

Hallucination Detection on SLAKE Open-Ended

79.94AUCVIHD
39.109649.709860.3170.9102Jan 26, 2026Feb 14, 2026Mar 5, 2026Mar 24, 2026Apr 12, 2026May 1, 2026May 20, 2026

Evaluation results

MethodLinks
VIHDBackbone=Hulu-4B2026.0579.9481.11
VIHDBackbone=Lingshu-7B2026.0575.3688.61
VASEBackbone=Hulu-4B2026.0574.4179.12
VASEBackbone=Lingshu-7B2026.0572.3785.06
V-LoopBackbone=Lingshu-7B2026.0167.6884.01
RadFlagBackbone=InternVL3-8B, Uncertainty-based=true2026.0164.9358.76
V-LoopBackbone=MedGemma-4B-it2026.0161.8768.6
SEBackbone=MedGemma-4B-it, Uncertainty-based=true2026.0160.968.42
MaxEntBackbone=Hulu-4B2026.0560.4568.22
AvgEntBackbone=Hulu-4B2026.0560.3968.26
MaxProbBackbone=Hulu-4B2026.0560.3768.21
AvgProbBackbone=Hulu-4B2026.0560.368.24
V-LoopBackbone=InternVL3-8B2026.0159.9759.77
MaxEntBackbone=InternVL3-8B2026.0159.5354.51
RadFlagBackbone=MedGemma-4B-it, Uncertainty-based=true2026.0159.1863.57
AvgEntBackbone=InternVL3-8B2026.0158.4754.34
SEBackbone=InternVL3-8B, Uncertainty-based=true2026.0158.2454.03
RadFlagBackbone=Lingshu-7B2026.0557.0777.14
MaxEntBackbone=MedGemma-4B-it2026.0156.5960.89
AvgEntBackbone=MedGemma-4B-it2026.0155.9860.72
MaxEntBackbone=Lingshu-7B2026.0553.9975.82
AvgEntBackbone=Lingshu-7B2026.0553.9775.82
AvgProbBackbone=Lingshu-7B2026.0553.9475.76
MaxProbBackbone=Lingshu-7B2026.0553.9375.75
RadFlagBackbone=Lingshu-7B, Uncertainty-based=true2026.0153.2975.05
MaxEntBackbone=Lingshu-7B2026.0153.1674.39
AvgEntBackbone=Lingshu-7B2026.0153.1374.38
SEBackbone=Lingshu-7B2026.0552.7274.13
SEBackbone=Lingshu-7B, Uncertainty-based=true2026.0150.5873.61
RadFlagBackbone=Hulu-4B2026.055059.02
SEBackbone=Hulu-4B2026.0549.2959.02
AvgProbBackbone=Lingshu-7B2026.0146.8770.07
MaxProbBackbone=Lingshu-7B2026.0146.8469.82
AvgProbBackbone=MedGemma-4B-it2026.0144.0258.77
MaxProbBackbone=MedGemma-4B-it2026.0143.2656.83
AvgProbBackbone=InternVL3-8B2026.0141.6246.91
MaxProbBackbone=InternVL3-8B2026.0140.6845.28