Med-StepBench is the first large-scale step-wise hallucination benchmark for 3D oncological PET/CT that decomposes clinical reasoning into four stages and reveals systematic VLM failures hidden by aggregate metrics.
Worse than random? an embarrassingly simple probing evaluation of large multimodal models in medical vqa
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Med-StepBench: A Hierarchical Reasoning Framework for Evaluating Hallucinations in Medical Vision-Language Models
Med-StepBench is the first large-scale step-wise hallucination benchmark for 3D oncological PET/CT that decomposes clinical reasoning into four stages and reveals systematic VLM failures hidden by aggregate metrics.