Uncertainty-Driven Expert Control: Enhancing the Reliability of Medical Vision-Language Models

TL;DR

This paper introduces an expert-in-the-loop framework called Expert-CFG that improves medical vision-language models by estimating uncertainty, retrieving relevant references, and guiding outputs without additional training, enhancing reliability in clinical applications.

Contribution

The proposed Expert-CFG framework aligns MedVLM with clinical expertise using uncertainty estimation and reference retrieval, avoiding costly retraining and improving model reliability.

Findings

Outperforms state-of-the-art models with fewer parameters.

Effective in resource-limited clinical settings.

Demonstrates improved accuracy on medical visual question answering benchmarks.

Abstract

The rapid advancements in Vision Language Models (VLMs) have prompted the development of multi-modal medical assistant systems. Despite this progress, current models still have inherent probabilistic uncertainties, often producing erroneous or unverified responses-an issue with serious implications in medical applications. Existing methods aim to enhance the performance of Medical Vision Language Model (MedVLM) by adjusting model structure, fine-tuning with high-quality data, or through preference fine-tuning. However, these training-dependent strategies are costly and still lack sufficient alignment with clinical expertise. To address these issues, we propose an expert-in-the-loop framework named Expert-Controlled Classifier-Free Guidance (Expert-CFG) to align MedVLM with clinical expertise without additional training. This framework introduces an uncertainty estimation strategy to identify unreliable outputs. It then retrieves relevant references to assist experts in highlighting key terms and applies classifier-free guidance to refine the token embeddings of MedVLM, ensuring that the adjusted outputs are correct and align with expert highlights. Evaluations across three medical visual question answering benchmarks demonstrate that the proposed Expert-CFG, with 4.2B parameters and limited expert annotations, outperforms state-of-the-art models with 13B parameters. The results demonstrate the feasibility of deploying such a system in resource-limited settings for clinical use.