Evaluating the Diagnostic Robustness of Vision-Language Models Under Visual and Textual Perturbations

• URL: http://arxiv.org/abs/2608.04885v1
• Date: Wed, 05 Aug 2026 14:09:55 GMT
• Title: Evaluating the Diagnostic Robustness of Vision-Language Models Under Visual and Textual Perturbations
• Abstract summary: We assess the diagnostic robustness of four VLM families under evidence-preserving perturbations.<n>Our results reveal significant vulnerabilities in presentation-order stability, with models exhibiting prediction flips in up to 48.9% of cases.
• Score: 3.765860543344957
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Standard accuracy metrics for VLMs often mask significant reliability failures in sensitive domains. In this work, we utilize a histopathology-validated brain MRI dataset to systematically assess the diagnostic robustness of four VLM families under evidence-preserving perturbations. By reordering anatomical slices and swapping target label positions, we evaluate whether models maintain consistent predictions when clinical evidence remains invariant. Our results reveal significant vulnerabilities in presentation-order stability, with models exhibiting prediction flips in up to 48.9% of cases under simple sequence reversals. We further identify a textual selection bias, where label reordering triggers inconsistent diagnoses in up to 67.8% of cases despite identical visual inputs. Negative-control tests further reveal diagnostic overcommitment: models generate categorical diagnoses in up to 76.1% of cases after expert-annotated lesion slices are removed. These results demonstrate that high accuracy can overestimate clinical reliability, masking sensitivity to sequential presentation and textual framing that is not captured by aggregate accuracy. Our findings highlight the necessity of stability-based metrics for the deployment of VLMs in safety-critical clinical applications. Our evaluation data and code will be made public upon acceptance.

Related papers

• When Confidence Fails: Overconfidence in LLMs under Uncertainty and Missing Clinical Information [14.659028787864996]
  Large Language Models (LLMs) have achieved strong performance in medical question answering and clinical reasoning tasks.<n>We conduct a behavioral analysis of LLMs under clinical information uncertainty.<n>We observe significant variation across models in their ability to abstain when the correct answer is unavailable.
  arXiv  Detail & Related papers  (2026-08-10T03:28:46Z)
• Beyond Scalar Scores: Exploring LLM-based Metrics for Clinical Significance Evaluation in Radiology Reports [49.5225801722164]
  Existing metrics obscure this requirement by reducing report quality to a medically ungrounded scalar.<n>We study this boundary using ReEvalMed benchmark as testbed and evaluate metric-level clinical significance.
  arXiv  Detail & Related papers  (2026-06-17T08:10:30Z)
• Benchmarking Multi-turn Medical Diagnosis: Hold, Lure, and Self-Correction [72.89352076103889]
  Large language models (LLMs) achieve high accuracy in medical diagnosis when all clinical information is provided in a single turn.<n>We introduce MINT, a high-fidelity, multi-turn medical diagnosis benchmark comprising 1,035 cases.<n>We uncover three persistent behavioral patterns that significantly impact diagnostic decisions.
  arXiv  Detail & Related papers  (2026-04-06T00:23:10Z)
• Mind the Rarities: Can Rare Skin Diseases Be Reliably Diagnosed via Diagnostic Reasoning? [31.103598483020857]
  Large vision-language models (LVLMs) demonstrate strong performance in dermatology.<n> evaluating diagnostic reasoning for rare conditions remains largely unexplored.<n>Our dataset contains 26,030 multi-modal image-text pairs and 6,354 clinically challenging cases.<n> Benchmarking 22 leading LVLMs exposes significant deficiencies across diagnosis accuracy, differential diagnosis, and clinical reasoning.
  arXiv  Detail & Related papers  (2026-03-19T02:25:36Z)
• Guideline-Grounded Evidence Accumulation for High-Stakes Agent Verification [60.18369393468405]
  Existing verifiers usually underperform owing to a lack of domain knowledge and limited calibration.<n>GLEAN compiles expert-curated protocols into trajectory-informed, well-calibrated correctness signals.<n>We empirically validate GLEAN with agentic clinical diagnosis across three diseases from the MIMIC-IV dataset.
  arXiv  Detail & Related papers  (2026-03-03T09:36:43Z)
• Toward Guarantees for Clinical Reasoning in Vision Language Models via Formal Verification [12.60121003165514]
  Vision-language models (VLMs) show promise in drafting radiology reports, yet they frequently suffer from logical inconsistencies.<n>Standard lexical metrics heavily penalize clinical paraphrasing and fail to capture these deductive failures.<n>We introduce a neurosymbolic verification framework that deterministically audits the internal consistency of VLM-generated reports.
  arXiv  Detail & Related papers  (2026-02-27T15:49:59Z)
• Diagnostics for Individual-Level Prediction Instability in Machine Learning for Healthcare [0.0]
  We propose an evaluation framework that quantifies individual-level prediction instability by using two complementary diagnostics.<n>We apply these diagnostics to simulated data and GUSTO-I clinical dataset.
  arXiv  Detail & Related papers  (2026-02-27T03:42:28Z)
• EchoBench: Benchmarking Sycophancy in Medical Large Vision-Language Models [82.43729208063468]
  Recent benchmarks for medical Large Vision-Language Models (LVLMs) emphasize leaderboard accuracy, overlooking reliability and safety.<n>We study sycophancy -- models' tendency to uncritically echo user-provided information.<n>We introduce EchoBench, a benchmark to systematically evaluate sycophancy in medical LVLMs.
  arXiv  Detail & Related papers  (2025-09-24T14:09:55Z)
• Beyond Benchmarks: Dynamic, Automatic And Systematic Red-Teaming Agents For Trustworthy Medical Language Models [87.66870367661342]
  Large language models (LLMs) are used in AI applications in healthcare.<n>Red-teaming framework that continuously stress-test LLMs can reveal significant weaknesses in four safety-critical domains.<n>A suite of adversarial agents is applied to autonomously mutate test cases, identify/evolve unsafe-triggering strategies, and evaluate responses.<n>Our framework delivers an evolvable, scalable, and reliable safeguard for the next generation of medical AI.
  arXiv  Detail & Related papers  (2025-07-30T08:44:22Z)
• Embeddings to Diagnosis: Latent Fragility under Agentic Perturbations in Clinical LLMs [0.0]
  We propose a geometry-aware evaluation framework, LAPD (Latent Agentic Perturbation Diagnostics), which probes the latent robustness of clinical LLMs under structured adversarial edits.<n>Within this framework, we introduce Latent Diagnosis Flip Rate (LDFR), a model-agnostic diagnostic signal that captures representational instability when embeddings cross decision boundaries in PCA-reduced latent space.<n>Our results reveal a persistent gap between surface robustness and semantic stability, underscoring the importance of geometry-aware auditing in safety-critical clinical AI.
  arXiv  Detail & Related papers  (2025-07-27T16:48:53Z)
• PersonalizedUS: Interpretable Breast Cancer Risk Assessment with Local Coverage Uncertainty Quantification [2.6911061523689415]
  The current "golden standard" relies on manual BI-RADS scoring by clinicians, often leading to unnecessary biopsies and a significant mental health burden on patients and their families. We introduce PersonalizedUS, an interpretable machine learning system that leverages recent advances in conformal prediction to provide precise and personalized risk estimates. Concrete clinical benefits include up to a 65% reduction in requested biopsies among BI-RADS 4a and 4b lesions, with minimal to no missed cancer cases.
  arXiv  Detail & Related papers  (2024-08-28T00:47:55Z)
• Towards Reliable Medical Image Segmentation by Modeling Evidential Calibrated Uncertainty [57.023423137202485]
  Concerns regarding the reliability of medical image segmentation persist among clinicians.<n>We introduce DEviS, an easily implementable foundational model that seamlessly integrates into various medical image segmentation networks.<n>By leveraging subjective logic theory, we explicitly model probability and uncertainty for medical image segmentation.
  arXiv  Detail & Related papers  (2023-01-01T05:02:46Z)

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.