# Uncertainty Is Not a Safety Net for Clinical VQA, but Can It Anticipate Model Failure?

arXiv: https://arxiv.org/abs/2606.16583 · HTML: https://mlsanity.com/paper/2606.16583/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Medical vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 17 of its 45 references that are in the map.
- First posted on arXiv 15 Jun 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Medical vision-language models](https://mlsanity.com/mllm/medical-vision-language-models/)

## Builds on (most cited first, 17 of 17)

- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [PubMedQA: A Dataset for Biomedical Research Question Answering](https://mlsanity.com/paper/1909.06146/) (2019)
- [Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models](https://mlsanity.com/paper/2409.17146/) (2024)
- [INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection](https://mlsanity.com/paper/2402.03744/) (2024)
- [LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training](https://mlsanity.com/paper/2509.23661/) (2025)
- [MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understanding](https://mlsanity.com/paper/2501.18362/) (2025)
- [Medical Visual Question Answering: A Survey](https://mlsanity.com/paper/2111.10056/) (2021)
- [VL-Uncertainty: Detecting Hallucination in Large Vision-Language Model via Uncertainty Estimation](https://mlsanity.com/paper/2411.11919/) (2024)
- [MedExQA: Medical Question Answering Benchmark with Multiple Explanations](https://mlsanity.com/paper/2406.06331/) (2024)
- [Combining Confidence Elicitation and Sample-based Methods for Uncertainty Quantification in Misinformation Mitigation](https://mlsanity.com/paper/2401.08694/) (2024)
- [Certainly Uncertain: A Benchmark and Metric for Multimodal Epistemic and Aleatoric Awareness](https://mlsanity.com/paper/2407.01942/) (2024)
- [ViLU: Learning Vision-Language Uncertainties for Failure Prediction](https://mlsanity.com/paper/2507.07620/) (2025)
- [Vision-Language and Large Language Model Performance in Gastroenterology: GPT, Claude, Llama, Phi, Mistral, Gemma, and Quantized Models](https://mlsanity.com/paper/2409.00084/) (2024)
- [Exploiting the Asymmetric Uncertainty Structure of Pre-trained VLMs on the Unit Hypersphere](https://mlsanity.com/paper/2505.11029/) (2025)
- [Calibrated? Not for Everyone: How Sexual Orientation and Religious Markers Distort LLM Accuracy and Confidence in Medical QA](https://mlsanity.com/paper/2604.17316/) (2026)
- [Unexplored flaws in multiple-choice VQA make benchmarking unreliable](https://mlsanity.com/paper/2511.22341/) (2025)

## Abstract (arXiv)

Safe deployment of clinical vision-language models (VLMs) requires reliable uncertainty estimation (UE): a signal indicating when predictions should be trusted or escalated to a clinician. We test whether current UE methods actually deliver this signal. Benchmarking 8 methods across 12 VLMs on clinical visual question-answering (VQA), we find that UE quality is not an intrinsic property of the UE method: it tracks model accuracy, degrading precisely where the model performance is weakest, and therefore where reliability is most needed. When we stress-test models by hiding the correct option among the multiple-choice answers (NOTA perturbations), accuracy collapses while uncertainty barely changes, leaving models systematically miscalibrated. Yet, we find that uncertainty on the unperturbed input reliably anticipates which predictions will collapse under NOTA, indicating that UE in current VLMs carries diagnostic information about model fragility. Our results position UE as a diagnostic tool for identifying fragile predictions and motivate perturbation-based evaluation as a path toward safe clinical deployment.