List your company

Hallucination Detection on PathVQA

82AUCCEBaG
28.4442.34556.2570.155Mar 23, 2026

Evaluation results

MethodLinks
CEBaGMLLM Backbone=HuatuoGPT-Vision-7B2026.038255.6
CEBaGMLLM Backbone=LLaVA-Med-v1.5-Mistral-7B2026.0377.653.1
AvgProbMLLM Backbone=LLaVA-Med-v1.5-Mistral-7B2026.0375.152
CEBaGMLLM Backbone=MedGemma-4b-it2026.0371.959
CEBaGMLLM Backbone=MedGemma-1.5-4b-it2026.0366.648.8
AvgProbMLLM Backbone=MedGemma-1.5-4b-it2026.0365.948.9
VASEMLLM Backbone=MedGemma-4b-it2026.0361.549.6
VASEMLLM Backbone=LLaVA-Med-v1.5-Mistral-7B2026.0360.441.7
VASEMLLM Backbone=MedGemma-1.5-4b-it2026.0360.145.7
RadFlagMLLM Backbone=LLaVA-Med-v1.5-Mistral-7B2026.0358.839.7
SEMLLM Backbone=MedGemma-4b-it2026.035848.9
SEMLLM Backbone=LLaVA-Med-v1.5-Mistral-7B2026.0357.441.3
RadFlagMLLM Backbone=MedGemma-4b-it2026.0356.847.4
SEMLLM Backbone=MedGemma-1.5-4b-it2026.0356.840.9
RadFlagMLLM Backbone=MedGemma-1.5-4b-it2026.0356.341.6
RadFlagMLLM Backbone=HuatuoGPT-Vision-7B2026.0355.538.9
SEMLLM Backbone=HuatuoGPT-Vision-7B2026.0353.638.2
VASEMLLM Backbone=HuatuoGPT-Vision-7B2026.0353.239.5
AvgProbMLLM Backbone=MedGemma-4b-it2026.0346.445.1
AvgProbMLLM Backbone=HuatuoGPT-Vision-7B2026.0330.528.7