W. Liu

CARE-MVLM: Counterfactual Abstention and Region-Grounded Evidence in Mammography Vision-Language Models

Accuracy Overstates Evidence Grounding and Abstention Reliability in Mammography Vision-Language Models

An evidence-grounded selective evaluation benchmark that evaluates Pathology classification and Abnormality identification together with label-aware lesion localization suggests that answer accuracy and abstention behavior can substantially overstate the reliability of current VLM when predictions are not verified agai...