# Analysis of Image-and-Text Uncertainty Propagation in Multimodal Large Language Models with Cardiac MR-Based Applications

arXiv: https://arxiv.org/abs/2507.12945 · HTML: https://mlsanity.com/paper/2507.12945/

## 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 17 of its 28 references that are in the map.
- First posted on arXiv 17 Jul 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, 17 of 17)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day](https://mlsanity.com/paper/2306.00890/) (2023)
- [Measuring Calibration in Deep Learning](https://mlsanity.com/paper/1904.01685/) (2019)
- [Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks](https://mlsanity.com/paper/1807.07356/) (2018)
- [M3D: Advancing 3D Medical Image Analysis with Multi-Modal Large Language Models](https://mlsanity.com/paper/2404.00578/) (2024)
- [VL-Uncertainty: Detecting Hallucination in Large Vision-Language Model via Uncertainty Estimation](https://mlsanity.com/paper/2411.11919/) (2024)
- [Uncertainty-Aware Evaluation for Vision-Language Models](https://mlsanity.com/paper/2402.14418/) (2024)
- [Training-Free Uncertainty Estimation for Dense Regression: Sensitivity as a Surrogate](https://mlsanity.com/paper/1910.04858/) (2019)
- [Large Language Model (LLM) AI text generation detection based on transformer deep learning algorithm](https://mlsanity.com/paper/2405.06652/) (2024)
- [MedDM:LLM-executable clinical guidance tree for clinical decision-making](https://mlsanity.com/paper/2312.02441/) (2023)
- [Exploring Response Uncertainty in MLLMs: An Empirical Evaluation under Misleading Scenarios](https://mlsanity.com/paper/2411.02708/) (2024)
- [Unveiling Uncertainty: A Deep Dive into Calibration and Performance of Multimodal Large Language Models](https://mlsanity.com/paper/2412.14660/) (2024)
- [Rethinking Uncertainty Estimation in LLMs: A Principled Single-Sequence Measure](https://mlsanity.com/paper/2412.15176/) (2024)
- [Exploring Large Language Models for Multi-Modal Out-of-Distribution Detection](https://mlsanity.com/paper/2310.08027/) (2023)
- [A versatile foundation model for cine cardiac magnetic resonance image analysis tasks](https://mlsanity.com/paper/2506.00679/) (2025)

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

- [Uncertainty-Aware Decision Making in Multimodal Large Language Models](https://mlsanity.com/paper/2608.17084/) (2026)

## Abstract (arXiv)

Multimodal large language models (MLLMs) can process and integrate information from multimodality sources, such as text and images. However, interrelationship among input modalities, uncertainties due to individual uni-modal data and potential clinical applications following such an uncertainty decomposition are yet fully understood in the context of large-scale MLLMs. In this work, we propose a multimodal uncertainty propagation model (MUPM) based on uncertainty propagation, to characterise the relationship among the uncertainties arising from image-only, text-only, and joint image-text variations in MLLM inputs. Using real clinical data consisting of cardiac MR scans and digital health records, we describe that MUPMs can be optimised robustly with a few samples. We then show that the fitted MUPMs are generalisable across different input data distributions and, perhaps surprisingly, across different downstream tasks. Such a transferability may be explained by the shared pretraining, comparatively light MLLM fine-tuning, along with the low-dimensional nature of the MUPMs. More importantly, this learned transferability, quantifying the relationship between these uncertainties, led to direct clinical applications in which uncertainties may be estimated and thus analysed robustly for varying data or even a novel set of cardiac disease prediction tasks. In addition, we show experimentally the efficiency in multimodal data required for estimating the overall uncertainty and its ability to identify redundant factors, both of which are considered practical yet clinically useful applications with the proposed MUPMs. Codes are available at https://github.com/yucheng722/MUPM.