# Worse than Random? An Embarrassingly Simple Probing Evaluation of Large Multimodal Models in Medical VQA

arXiv: https://arxiv.org/abs/2405.20421 · HTML: https://mlsanity.com/paper/2405.20421/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Placed in Medical vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 23 of its 40 references that are in the map.
- First posted on arXiv 30 May 2024.

## Placed in

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

## Builds on (most cited first, 23 of 23)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day](https://mlsanity.com/paper/2306.00890/) (2023)
- [ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases](https://mlsanity.com/paper/1705.02315/) (2017)
- [The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)](https://mlsanity.com/paper/2309.17421/) (2023)
- [MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning](https://mlsanity.com/paper/2310.09478/) (2023)
- [Large Language Models Are Not Robust Multiple Choice Selectors](https://mlsanity.com/paper/2309.03882/) (2023)
- [PathVQA: 30000+ Questions for Medical Visual Question Answering](https://mlsanity.com/paper/2003.10286/) (2020)
- [SLAKE: A Semantically-Labeled Knowledge-Enhanced Dataset for Medical Visual Question Answering](https://mlsanity.com/paper/2102.09542/) (2021)
- [PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering](https://mlsanity.com/paper/2305.10415/) (2023)
- [A Study of Generative Large Language Model for Medical Research and Healthcare](https://mlsanity.com/paper/2305.13523/) (2023)
- [A Survey of Large Language Models for Healthcare: from Data, Technology, and Applications to Accountability and Ethics](https://mlsanity.com/paper/2310.05694/) (2023)
- [A Survey of Large Language Models in Medicine: Progress, Application, and Challenge](https://mlsanity.com/paper/2311.05112/) (2023)
- [Can GPT-4V(ision) Serve Medical Applications? Case Studies on GPT-4V for Multimodal Medical Diagnosis](https://mlsanity.com/paper/2310.09909/) (2023)
- [MedICaT: A Dataset of Medical Images, Captions, and Textual References](https://mlsanity.com/paper/2010.06000/) (2020)
- ["My Answer is C": First-Token Probabilities Do Not Match Text Answers in Instruction-Tuned Language Models](https://mlsanity.com/paper/2402.14499/) (2024)
- [MedBLIP: Bootstrapping Language-Image Pre-training from 3D Medical Images and Texts](https://mlsanity.com/paper/2305.10799/) (2023)
- [Multimodal ChatGPT for Medical Applications: an Experimental Study of GPT-4V](https://mlsanity.com/paper/2310.19061/) (2023)
- [Fool Your (Vision and) Language Model With Embarrassingly Simple Permutations](https://mlsanity.com/paper/2310.01651/) (2023)
- [Holistic Evaluation of GPT-4V for Biomedical Imaging](https://mlsanity.com/paper/2312.05256/) (2023)

## Built on by (most cited first, 19 of 19)

- [MedFrameQA: A Multi-Image Medical VQA Benchmark for Clinical Reasoning](https://mlsanity.com/paper/2505.16964/) (2025)
- [WildHallucinations: Evaluating Long-form Factuality in LLMs with Real-World Entity Queries](https://mlsanity.com/paper/2407.17468/) (2024)
- [Uni-Med: A Unified Medical Generalist Foundation Model For Multi-Task Learning Via Connector-MoE](https://mlsanity.com/paper/2409.17508/) (2024)
- [Language Models are Surprisingly Fragile to Drug Names in Biomedical Benchmarks](https://mlsanity.com/paper/2406.12066/) (2024)
- [A Survey on Trustworthiness in Foundation Models for Medical Image Analysis](https://mlsanity.com/paper/2407.15851/) (2024)
- [Localizing Before Answering: A Hallucination Evaluation Benchmark for Grounded Medical Multimodal LLMs](https://mlsanity.com/paper/2505.00744/) (2025)
- [Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis](https://mlsanity.com/paper/2505.22079/) (2025)
- [MedMax: Mixed-Modal Instruction Tuning for Training Biomedical Assistants](https://mlsanity.com/paper/2412.12661/) (2024)
- [Structure Causal Models and LLMs Integration in Medical Visual Question Answering](https://mlsanity.com/paper/2505.02703/) (2025)
- [Insights into a radiology-specialised multimodal large language model with sparse autoencoders](https://mlsanity.com/paper/2507.12950/) (2025)
- [Vision-language models for chest radiography do not always need the image](https://mlsanity.com/paper/2606.17710/) (2026)
- [Tonguescape: Exploring Language Models Understanding of Vowel Articulation](https://mlsanity.com/paper/2501.17643/) (2025)
- [AMANDA: Agentic Medical Knowledge Augmentation for Data-Efficient Medical Visual Question Answering](https://mlsanity.com/paper/2510.02328/) (2025)
- [Bridging the Gap Between Multimodal Foundation Models and World Models](https://mlsanity.com/paper/2510.03727/) (2025)
- [Exploring SAIG Methods for an Objective Evaluation of XAI](https://mlsanity.com/paper/2602.08715/) (2026)
- [Aloe-Vision: Robust Vision-Language Models for Healthcare](https://mlsanity.com/paper/2606.27500/) (2026)
- [MultiMedEdit: A Scenario-Aware Benchmark for Evaluating Knowledge Editing in Medical VQA](https://mlsanity.com/paper/2508.07022/) (2025)
- [Toward Automatic Safe Driving Instruction: A Large-Scale Vision Language Model Approach](https://mlsanity.com/paper/2511.23311/) (2025)
- [How Good LLMs Are at Answering Bangla Medical Visual Questions? Dataset and Benchmarking](https://mlsanity.com/paper/2605.18111/) (2026)

## Abstract (arXiv)

Large Multimodal Models (LMMs) have shown remarkable progress in medical Visual Question Answering (Med-VQA), achieving high accuracy on existing benchmarks. However, their reliability under robust evaluation is questionable. This study reveals that when subjected to simple probing evaluation, state-of-the-art models perform worse than random guessing on medical diagnosis questions. To address this critical evaluation problem, we introduce the Probing Evaluation for Medical Diagnosis (ProbMed) dataset to rigorously assess LMM performance in medical imaging through probing evaluation and procedural diagnosis. Particularly, probing evaluation features pairing original questions with negation questions with hallucinated attributes, while procedural diagnosis requires reasoning across various diagnostic dimensions for each image, including modality recognition, organ identification, clinical findings, abnormalities, and positional grounding. Our evaluation reveals that top-performing models like GPT-4o, GPT-4V, and Gemini Pro perform worse than random guessing on specialized diagnostic questions, indicating significant limitations in handling fine-grained medical inquiries. Besides, models like LLaVA-Med struggle even with more general questions, and results from CheXagent demonstrate the transferability of expertise across different modalities of the same organ, showing that specialized domain knowledge is still crucial for improving performance. This study underscores the urgent need for more robust evaluation to ensure the reliability of LMMs in critical fields like medical diagnosis, and current LMMs are still far from applicable to those fields.