List your company

Hallucination Detection on SLAKE (All)

78.91AUCVIHD
38.838849.241959.64570.0481Jan 26, 2026Feb 14, 2026Mar 5, 2026Mar 24, 2026Apr 12, 2026May 1, 2026May 20, 2026

Evaluation results

MethodLinks
VIHDBackbone=Hulu-4B2026.0578.9184.96
VIHDBackbone=Lingshu-7B2026.0572.9586.49
VASEBackbone=Lingshu-7B2026.0570.5684.52
VASEBackbone=Hulu-4B2026.0570.3181.27
RadFlagBackbone=InternVL3-8B, Uncertainty-based=true2026.0162.1259.75
SEBackbone=InternVL3-8B, Uncertainty-based=true2026.0160.6158.31
V-LoopBackbone=Lingshu-7B2026.0159.7981.83
RadFlagBackbone=MedGemma-4B-it, Uncertainty-based=true2026.0159.5658.53
V-LoopBackbone=MedGemma-4B-it2026.0159.3165.15
MaxProbBackbone=Hulu-4B2026.0559.2672.62
MaxEntBackbone=Hulu-4B2026.0559.2472.61
AvgProbBackbone=Hulu-4B2026.0559.1372.59
AvgEntBackbone=Hulu-4B2026.0559.0372.56
MaxEntBackbone=InternVL3-8B2026.0158.8155.93
AvgEntBackbone=InternVL3-8B2026.0158.0955.58
MaxEntBackbone=MedGemma-4B-it2026.0157.4557.23
AvgEntBackbone=MedGemma-4B-it2026.0156.9857.2
SEBackbone=MedGemma-4B-it, Uncertainty-based=true2026.0156.8459.62
V-LoopBackbone=InternVL3-8B2026.0156.0457.96
RadFlagBackbone=Lingshu-7B2026.0555.4678.25
MaxEntBackbone=Lingshu-7B2026.0553.3777.44
AvgEntBackbone=Lingshu-7B2026.0553.3477.42
AvgProbBackbone=Lingshu-7B2026.0553.377.39
MaxProbBackbone=Lingshu-7B2026.0553.377.38
AvgEntBackbone=Lingshu-7B2026.0153.2575.65
MaxEntBackbone=Lingshu-7B2026.0153.2575.65
RadFlagBackbone=Lingshu-7B, Uncertainty-based=true2026.0152.5275.44
SEBackbone=Lingshu-7B2026.0552.4576.44
SEBackbone=Lingshu-7B, Uncertainty-based=true2026.0150.8975.61
RadFlagBackbone=Hulu-4B2026.055068.12
SEBackbone=Hulu-4B2026.0549.366.89
AvgProbBackbone=Lingshu-7B2026.0146.7569.97
MaxProbBackbone=Lingshu-7B2026.0146.7570.09
AvgProbBackbone=MedGemma-4B-it2026.0143.0156.26
MaxProbBackbone=MedGemma-4B-it2026.0142.6555.02
AvgProbBackbone=InternVL3-8B2026.0141.2446.19
MaxProbBackbone=InternVL3-8B2026.0140.3844.39