Med-StepBench: A Hierarchical Reasoning Framework for Evaluating Hallucinations in Medical Vision-Language Models
Authors: Minh Khoi Nguyen, Dai Lam Le, Amir Reza Jafari, Tuan Dung Nguyen, Mai Hong Son, Mai Huy Thong, Quang Huy Nguyen, Thanh Trung Nguyen, +3 more
Organizations: 1AI4LIFE, Hanoi University of Science and Technology, Vietnam · 2SAMOVAR, Télécom SudParis, Institut Polytechnique de Paris, France · Military Central Hospital, Vietnam · 4Hanoi Medical University
Abstract
Large vision-language models (VLMs) demonstrate strong performance in medical image understanding, but frequently generate clinically plausible yet incorrect statements, raising significant safety concerns. Existing medical hallucination benchmarks primarily focus on 2D imaging with one-shot diagnostic questions, offering limited insight into whether predictions are grounded in correct localization and abnormality identification, allowing critical reasoning errors to remain hidden behind seemingly correct diagnoses. We introduce Med-StepBench, the first large-scale benchmark for step-wise hallucination detection in 3D oncological PET/CT, comprising over 12,000 images and more than 1,000,000 image-statement pairs across volumetric and multi-view 2D data, which decomposes clinical reasoning into four expert-designed diagnostic stages. Using clinician-verified annotations, we perform the first step-level evaluation of general-purpose and medical VLMs, revealing systematic failure modes obscured by aggregate accuracy metrics. Furthermore, we show that current VLMs are highly susceptible to adversarial yet clinically plausible intermediate explanations, which significantly amplify hallucinations despite contradictory visual evidence. Together, our findings highlight fundamental limitations in grounding multi-step clinical reasoning and establish Med-StepBench as a rigorous benchmark for developing safer and more reliable medical VLMs.
Vision-language models (VLMs) are increasingly used for medical image interpretation, yet they frequently hallucinate, generating clinically plausible but factually incorrect findings that pose direct patient safety risks. We introduce HalluCXR, a benchmark evaluating six architecturally diverse VLMs across 856 stratified MIMIC-CXR chest radiographs and three query types, yielding 15,408 model evaluations. An eight-category hallucination taxonomy with clinical severity ratings and a two-layer detection pipeline are validated against 250 human annotations (auto-detection F1=0.959; LLM judge F1=0.907). We find that 61.9--82.3% of outputs contain hallucinations, with clinically dangerous errors in up to 80.2%. Three key patterns emerge: normal radiographs paradoxically attract the most severe hallucinations, common findings are systematically over-fabricated while rare findings go under-detected, and response length alone predicts hallucination risk (AUC up to 0.908). A six-model ensemble reduces fabrication by up to 84.8% at the cost of increased omission; a three-model subset retains comparable performance at half the cost. These results establish that hallucination auditing, verbosity-based risk monitoring, and ensemble-based safety layers are prerequisites for clinical deployment.
Building trustworthy medical multimodal large language models (MLLMs) is critical for reliable clinical decision support. Existing medical hallucination benchmarks mainly focus on data collection, but often ignore where hallucinations originate within the reasoning process. We find that hallucination sources vary across samples: errors may arise from visual misrecognition, incorrect medical knowledge recall, or flawed reasoning integration. To enable source-level hallucination diagnosis, we introduce ClinHallu, a benchmark for stage-wise hallucination diagnosis in medical MLLM reasoning. ClinHallu contains 7,031 validated instances, where each instance is augmented with a structured reasoning trace decomposed into Visual Recognition, Knowledge Recall, and Reasoning Integration. We also use stage-replacement interventions to measure how correcting specific stages affects the final answer. Beyond evaluation, we show that trace-supervised fine-tuning reduces stage-wise hallucinations. ClinHallu provides a fine-grained hallucination testbed for diagnosing and mitigating reasoning failures in medical MLLMs. The benchmark is publicly available at https://github.com/alibaba-damo-academy/ClinHallu.
Large vision-language models (LVLMs) are increasingly used for clinical image understanding, yet they remain vulnerable to \emph{hallucinations}--producing textual findings or attributes not supported by the image. We present a vision-traceable hallucination detection framework that audits arbitrary LVLM responses via visual evidence grounding, requiring neither modification nor internal access to the hidden states of LVLMs. Given an LVLM response, we extract visually verifiable entities and use a medical-domain-adapted Qwen-VL grounding verifier to localize each entity on the input image. To enhance the robustness of our detection method, we introduce a counterfactual entity perturbation method and estimate visual evidence uncertainty by contrasting factual and counterfactual grounding results. Specifically, we compute an entity-level uncertainty score from the positive confidence, counterfactual confidence, and their grounding overlap for binary hallucination decision-making. Experiments on multiple medical imaging modalities and LVLM backbones demonstrate that our method consistently improves hallucination detection performance over recent baselines, while providing interpretable localization evidence and strong cross-model transferability. Code and dataset are available at https://github.com/Agentic-CliniAI/CounterVHD.