# Why Text Prevails: Vision May Undermine Multimodal Medical Decision Making

arXiv: https://arxiv.org/abs/2512.13747 · HTML: https://mlsanity.com/paper/2512.13747/

## Key facts

- Cited by 1 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 28 of its 42 references that are in the map.
- First posted on arXiv 15 Dec 2025.

## Placed in

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

## Builds on (most cited first, 28 of 28)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (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)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day](https://mlsanity.com/paper/2306.00890/) (2023)
- [BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs](https://mlsanity.com/paper/2303.00915/) (2023)
- [MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning](https://mlsanity.com/paper/2311.10537/) (2023)
- [MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Making](https://mlsanity.com/paper/2404.15155/) (2024)
- [MMedAgent: Learning to Use Medical Tools with Multi-modal Agent](https://mlsanity.com/paper/2407.02483/) (2024)
- [XrayGPT: Chest Radiographs Summarization using Medical Vision-Language Models](https://mlsanity.com/paper/2306.07971/) (2023)
- [REFUGE2 Challenge: A Treasure Trove for Multi-Dimension Analysis and Evaluation in Glaucoma Screening](https://mlsanity.com/paper/2202.08994/) (2022)
- [CPath-Omni: A Unified Multimodal Foundation Model for Patch and Whole Slide Image Analysis in Computational Pathology](https://mlsanity.com/paper/2412.12077/) (2024)
- [SLIDE: A Framework Integrating Small and Large Language Models for Open-Domain Dialogues Evaluation](https://mlsanity.com/paper/2405.15924/) (2024)
- [X-ray Made Simple: Lay Radiology Report Generation and Robust Evaluation](https://mlsanity.com/paper/2406.17911/) (2024)
- [SouLLMate: An Adaptive LLM-Driven System for Advanced Mental Health Support and Assessment, Based on a Systematic Application Survey](https://mlsanity.com/paper/2410.11859/) (2024)
- [SouLLMate: An Application Enhancing Diverse Mental Health Support with Adaptive LLMs, Prompt Engineering, and RAG Techniques](https://mlsanity.com/paper/2410.16322/) (2024)
- [Evaluating Open-Domain Dialogues in Latent Space with Next Sentence Prediction and Mutual Information](https://mlsanity.com/paper/2305.16967/) (2023)
- [Zeus: Zero-shot LLM Instruction for Union Segmentation in Multimodal Medical Imaging](https://mlsanity.com/paper/2504.07336/) (2025)
- [Constrained Multiview Representation for Self-supervised Contrastive Learning](https://mlsanity.com/paper/2402.03456/) (2024)
- [Interpretable Spatio-Temporal Embedding for Brain Structural-Effective Network with Ordinary Differential Equation](https://mlsanity.com/paper/2405.13190/) (2024)
- [A Heterogeneous Graph Neural Network Fusing Functional and Structural Connectivity for MCI Diagnosis](https://mlsanity.com/paper/2411.08424/) (2024)
- [DRE: An Effective Dual-Refined Method for Integrating Small and Large Language Models in Open-Domain Dialogue Evaluation](https://mlsanity.com/paper/2506.04516/) (2025)

## Built on by (most cited first, 1 of 1)

- [Physics-based phenomenological characterization of cross-modal bias in multimodal models](https://mlsanity.com/paper/2602.20624/) (2026)

## Abstract (arXiv)

With the rapid progress of large language models (LLMs), advanced multimodal large language models (MLLMs) have demonstrated impressive zero-shot capabilities on vision-language tasks. In the biomedical domain, however, even state-of-the-art MLLMs struggle with basic Medical Decision Making (MDM) tasks. We investigate this limitation using two challenging datasets: (1) three-stage Alzheimer's disease (AD) classification (normal, mild cognitive impairment, dementia), where category differences are visually subtle, and (2) MIMIC-CXR chest radiograph classification with 14 non-mutually exclusive conditions. Our empirical study shows that text-only reasoning consistently outperforms vision-only or vision-text settings, with multimodal inputs often performing worse than text alone. To mitigate this, we explore three strategies: (1) in-context learning with reason-annotated exemplars, (2) vision captioning followed by text-only inference, and (3) few-shot fine-tuning of the vision tower with classification supervision. These findings reveal that current MLLMs lack grounded visual understanding and point to promising directions for improving multimodal decision making in healthcare.