List your company

Hallucination Detection on VQA-RAD (All)

78.23AUCVIHD
37.077247.761158.44569.1289Jan 26, 2026Feb 14, 2026Mar 5, 2026Mar 24, 2026Apr 12, 2026May 1, 2026May 20, 2026

Evaluation results

MethodLinks
VIHDBackbone=Hulu-4B2026.0578.2380.82
VIHDBackbone=Lingshu-7B2026.0571.5870.86
VASEBackbone=Lingshu-7B2026.0569.6269.35
CEBaGMLLM Backbone=HuatuoGPT-Vision-7B2026.0367.767.6
CEBaGMLLM Backbone=MedGemma-1.5-4b-it2026.0366.958.2
VASEBackbone=Hulu-4B2026.0566.2371.51
RadFlagBackbone=InternVL3-8B, Uncertainty-based=true2026.0163.9957.98
AvgProbMLLM Backbone=MedGemma-1.5-4b-it2026.0363.656.2
CEBaGMLLM Backbone=LLaVA-Med-v1.5-Mistral-7B2026.0362.150
MaxEntBackbone=InternVL3-8B2026.0161.5957.14
MaxProbBackbone=Hulu-4B2026.0561.1766.98
MaxEntBackbone=Hulu-4B2026.0561.1266.98
V-LoopBackbone=InternVL3-8B2026.0160.9858.15
CEBaGMLLM Backbone=MedGemma-4b-it2026.0360.864.6
V-LoopBackbone=MedGemma-4B-it2026.0160.366.91
AvgProbBackbone=Hulu-4B2026.0560.1367.02
SEBackbone=InternVL3-8B, Uncertainty-based=true2026.0160.0456.01
RadFlagMLLM Backbone=HuatuoGPT-Vision-7B2026.036063.5
AvgEntBackbone=InternVL3-8B2026.0159.6754.34
AvgEntBackbone=Hulu-4B2026.0559.3266.88
VASEMLLM Backbone=HuatuoGPT-Vision-7B2026.0358.966.1
AvgProbMLLM Backbone=LLaVA-Med-v1.5-Mistral-7B2026.0358.848.7
RadFlagBackbone=MedGemma-4B-it, Uncertainty-based=true2026.0158.6957.94
SEMLLM Backbone=HuatuoGPT-Vision-7B2026.0358.365.1
SEMLLM Backbone=LLaVA-Med-v1.5-Mistral-7B2026.0358.150.7
VASEMLLM Backbone=MedGemma-4b-it2026.0357.659.9
VASEMLLM Backbone=LLaVA-Med-v1.5-Mistral-7B2026.0357.649.3
RadFlagMLLM Backbone=LLaVA-Med-v1.5-Mistral-7B2026.0356.848.1
SEBackbone=MedGemma-4B-it, Uncertainty-based=true2026.0156.6559.76
MaxEntBackbone=MedGemma-4B-it2026.0156.1158.97
AvgEntBackbone=MedGemma-4B-it2026.0155.658.33
VASEMLLM Backbone=MedGemma-1.5-4b-it2026.0354.851.5
AvgEntBackbone=Lingshu-7B2026.0554.859.34
MaxEntBackbone=Lingshu-7B2026.0554.7459.33
AvgProbBackbone=Lingshu-7B2026.0554.7259.29
MaxProbBackbone=Lingshu-7B2026.0554.7159.3
RadFlagMLLM Backbone=MedGemma-4b-it2026.0354.758.9
RadFlagMLLM Backbone=MedGemma-1.5-4b-it2026.0354.346.3
SEMLLM Backbone=MedGemma-1.5-4b-it2026.0353.448.6
RadFlagBackbone=Lingshu-7B2026.0552.9458.94
SEMLLM Backbone=MedGemma-4b-it2026.0352.258
MaxEntBackbone=Lingshu-7B2026.0151.7660.96
AvgEntBackbone=Lingshu-7B2026.0151.7360.96
RadFlagBackbone=Lingshu-7B, Uncertainty-based=true2026.0151.5559.29
SEBackbone=Lingshu-7B, Uncertainty-based=true2026.0150.9659.16
SEBackbone=Lingshu-7B2026.0550.9255.27
V-LoopBackbone=Lingshu-7B2026.0150.0462.84
RadFlagBackbone=Hulu-4B2026.055061.26
SEBackbone=Hulu-4B2026.0549.4862.24
AvgProbBackbone=Lingshu-7B2026.0148.2756.36
MaxProbBackbone=Lingshu-7B2026.0148.2455.44
AvgProbBackbone=MedGemma-4B-it2026.0144.4954.25
MaxProbBackbone=MedGemma-4B-it2026.0143.7153.12
AvgProbMLLM Backbone=MedGemma-4b-it2026.0342.954.6
AvgProbBackbone=InternVL3-8B2026.0139.7743.33
AvgProbMLLM Backbone=HuatuoGPT-Vision-7B2026.0339.352.2
MaxProbBackbone=InternVL3-8B2026.0138.6640.72