Med-R2: An Adversarial Benchmark for Evidence-Grounded Reasoning in Medical VLMs

• URL: http://arxiv.org/abs/2605.24492v1
• Date: Sat, 23 May 2026 09:50:19 GMT
• Title: Med-R2: An Adversarial Benchmark for Evidence-Grounded Reasoning in Medical VLMs
• Abstract summary: We introduce Med-R2 Bench, a hierarchical benchmark aligned with the clinical workflow to evaluate adversarial robustness with visual grounding.<n>We design stepwise QA tasks to assess whether reasoning chains are strictly grounded in visual evidence across the four clinical stages.
• Score: 21.95646908343504
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision-language models have demonstrated impressive capabilities in general medical visual question answering, yet due to limited interpretability, it remains unclear whether their predictions reflect evidence-grounded clinical reasoning or reliance on spurious priors. We introduce Med-R2 Bench, a hierarchical benchmark aligned with the clinical workflow to evaluate adversarial robustness with visual grounding. We design stepwise QA tasks to assess whether reasoning chains are strictly grounded in visual evidence across the four clinical stages, and employ adversarial perturbations to test robustness against misleading cues. Med-R2 comprises 42,432 images, 31 task categories, and 110,406 QA pairs. Evaluation across 14 VLMs reveals a sequential performance degradation along the four-stage clinical workflow. Adversarial experiments show that models rely heavily on correct prompts to guess answers. Even when provided with explicit visual cues, the models struggle to accurately align textual descriptions. Finally, we demonstrate stepwise fine-tuning using our hierarchical data significantly improves reasoning robustness, highlighting its potential to drive future improvements in evidence-based medical AI.

Related papers

• Analyzing and Improving Fine-grained Preference Optimization in Medical LVLMs [53.697403481143404]
  Large Vision-Language Models (LVLMs) have achieved strong performance across medical imaging tasks.<n>But they remain prone to factual inconsistencies, poor visual grounding, and misalignment with clinically meaningful feedback.
  arXiv  Detail & Related papers  (2026-06-10T18:35:36Z)
• VITAL: Visual-Semantic Dual Supervision for Enhanced and Interpretable Latent Reasoning in Medical MLLMs [42.047738141438344]
  VITAL is a latent-space reasoning framework for medical MLLMs with visual-semantic dual supervision.<n>We construct a 61K dataset spanning 9 imaging modalities, exceeding prior medical visual latent reasoning datasets by an order of magnitude.
  arXiv  Detail & Related papers  (2026-05-27T12:53:13Z)
• MedLVR: Latent Visual Reasoning for Reliable Medical Visual Question Answering [8.481971263315854]
  textscMedLVR introduces an explicit visual evidence state into autoretext decoding.<n>Latent visual reasoning provides an effective mechanism for preserving diagnostically relevant visual evidence.
  arXiv  Detail & Related papers  (2026-04-10T16:03:03Z)
• M3CoTBench: Benchmark Chain-of-Thought of MLLMs in Medical Image Understanding [66.78251988482222]
  Chain-of-Thought (CoT) reasoning has proven effective in enhancing large language models by encouraging step-by-step intermediate reasoning.<n>Current benchmarks for medical image understanding generally focus on the final answer while ignoring the reasoning path.<n>M3CoTBench aims to foster the development of transparent, trustworthy, and diagnostically accurate AI systems for healthcare.
  arXiv  Detail & Related papers  (2026-01-13T17:42:27Z)
• S-Chain: Structured Visual Chain-of-Thought For Medicine [81.97605645734741]
  We introduce S-Chain, the first large-scale dataset of 12,000 expert-annotated medical images with bounding boxes and structured visual CoT (SV-CoT)<n>The dataset further supports 16 languages, totaling over 700k VQA pairs for broad multilingual applicability.<n>S-Chain establishes a new benchmark for grounded medical reasoning and paves the way toward more trustworthy and explainable medical vision-language models.
  arXiv  Detail & Related papers  (2025-10-26T15:57:14Z)
• MedAlign: A Synergistic Framework of Multimodal Preference Optimization and Federated Meta-Cognitive Reasoning [52.064286116035134]
  We develop MedAlign, a framework to ensure visually accurate LVLM responses for Medical Visual Question Answering (Med-VQA)<n>We first propose a multimodal Direct Preference Optimization (mDPO) objective to align preference learning with visual context.<n>We then design a Retrieval-Aware Mixture-of-Experts (RA-MoE) architecture that utilizes image and text similarity to route queries to a specialized and context-augmented LVLM.
  arXiv  Detail & Related papers  (2025-10-24T02:11:05Z)
• Benchmarking and Mitigate Sycophancy in Medical Vision-Language Models [21.353225217216252]
  Vision language models often exhibit sycophantic behavior prioritizing alignment with user phrasing social cues or perceived authority over evidence based reasoning.<n>This study evaluate clinical sycophancy in medical visual question answering through a novel clinically grounded benchmark.
  arXiv  Detail & Related papers  (2025-09-26T07:02:22Z)
• Knowing or Guessing? Robust Medical Visual Question Answering via Joint Consistency and Contrastive Learning [34.6490677122246]
  We show that current Medical Vision-Language Models (Med-VLMs) exhibit concerning fragility in Medical Visual Question Answering.<n>We propose Consistency and Contrastive Learning (CCL), which integrates knowledge-anchored consistency learning and bias-aware contrastive learning.<n>CCL achieves SOTA performance on three popular VQA benchmarks and notably improves answer consistency by 50% on the challenging RoMed test set.
  arXiv  Detail & Related papers  (2025-08-26T05:21:19Z)
• Uncertainty-Driven Expert Control: Enhancing the Reliability of Medical Vision-Language Models [52.2001050216955]
  Existing methods aim to enhance the performance of Medical Vision Language Model (MedVLM) by adjusting model structure, fine-tuning with high-quality data, or through preference fine-tuning.<n>We propose an expert-in-the-loop framework named Expert-Controlled-Free Guidance (Expert-CFG) to align MedVLM with clinical expertise without additional training.
  arXiv  Detail & Related papers  (2025-07-12T09:03:30Z)
• GEMeX-RMCoT: An Enhanced Med-VQA Dataset for Region-Aware Multimodal Chain-of-Thought Reasoning [60.03671205298294]
  Medical visual question answering aims to support clinical decision-making by enabling models to answer natural language questions based on medical images.<n>Current methods still suffer from limited answer reliability and poor interpretability.<n>This work first proposes a Region-Aware Multimodal Chain-of-Thought dataset, in which the process of producing an answer is preceded by a sequence of intermediate reasoning steps.
  arXiv  Detail & Related papers  (2025-06-22T08:09:58Z)
• DeVisE: Behavioral Testing of Medical Large Language Models [14.832083455439749]
  DeVisE is a behavioral testing framework for probing fine-grained clinical understanding.<n>We construct a dataset of ICU discharge notes from MIMIC-IV.<n>We evaluate five LLMs spanning general-purpose and medically fine-tuned variants.
  arXiv  Detail & Related papers  (2025-06-18T10:42:22Z)
• Robust and Interpretable Medical Image Classifiers via Concept Bottleneck Models [49.95603725998561]
  We propose a new paradigm to build robust and interpretable medical image classifiers with natural language concepts. Specifically, we first query clinical concepts from GPT-4, then transform latent image features into explicit concepts with a vision-language model.
  arXiv  Detail & Related papers  (2023-10-04T21:57:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.