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

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

Contamination, Prior, or Evidence? Decomposing and Training Evidence Use in Whole-Slide Vision-Language Models

Pathology vision-language models (VLMs) are conventionally evaluated by accuracy, but accuracy alone does not measure evidence use: it may conflate dataset contamination, prior knowledge, and image evidence. In a motivating study of lymph-node metastasis prediction, we found that most public pathology VLMs showed minim...

An Automated, Contamination-Controlled VQA Benchmark for Evaluating Vision-Language Models on 3D Oncology Imaging

Vision-language models (VLMs) are increasingly applied to medical imaging, yet public benchmarks may reward memorization over perception: their images and questions can enter pretraining corpora, and many items remain answerable from question text alone. We present an automated, agent-driven pipeline that builds multip...

Do Accuracy Gains Reflect Genuine Visual Understanding? A Multi-Model Evaluation of Vision-Language Models in Thoracic Imaging.

Even at the highest accuracy observed here, answer-level performance can overstate visual understanding, pointing to the need for more appropriate evaluation methods that assess whether a model's reasoning is faithful to the image, not only whether its answer is correct.

CBEC: a simple retrieval-based framework for population-grounded prediction reliability estimation in chest X-ray diagnosis

It is suggested that case-level consistency provides a meaningful practical signal for reliability estimation in medical imaging, whose relationship to the classical epistemic–aleatoric decomposition warrants further theoretical investigation across broader clinical settings.

Knowing When Not to Answer: Abstention and Refusal Reasoning in Vision--Language Models

PARITY (Paired Assessment with Reused Identity), a synthetic, demographically balanced set of identity-controlled neutral/expression portrait pairs with neutral-neutral controls, is introduced, finding a clear split between refusal-first models and speculative models; in the latter, certain expressions disproportionate...