MedLayBench-V: A Large-Scale Benchmark for Expert-Lay Semantic Alignment in Medical Vision Language Models

2026-04-07

AI Summary

This work addresses the limitations of existing medical vision-language models, which are predominantly trained on specialized literature and struggle to explain imaging findings to patients in lay terms, while also lacking multimodal evaluation benchmarks that support semantic alignment between clinicians and non-experts. To bridge this gap, the authors introduce MedLayBench-V—the first large-scale multimodal benchmark designed explicitly for aligning expert and layperson semantics in medical contexts. By integrating Unified Medical Language System (UMLS) Concept Unique Identifiers (CUIs) with fine-grained entity constraints, they develop a Structured Concept-Grounded Refinement (SCGR) pipeline that generates hallucination-free, semantically equivalent lay descriptions, ensuring strict consistency between professional and patient-oriented language. This benchmark provides a high-quality, verifiable foundation for training and evaluating medical vision-language models tailored for patient communication.

Abstract

Medical Vision-Language Models (Med-VLMs) have achieved expert-level proficiency in interpreting diagnostic imaging. However, current models are predominantly trained on professional literature, limiting their ability to communicate findings in the lay register required for patient-centered care. While text-centric research has actively developed resources for simplifying medical jargon, there is a critical absence of large-scale multimodal benchmarks designed to facilitate lay-accessible medical image understanding. To bridge this resource gap, we introduce MedLayBench-V, the first large-scale multimodal benchmark dedicated to expert-lay semantic alignment. Unlike naive simplification approaches that risk hallucination, our dataset is constructed via a Structured Concept-Grounded Refinement (SCGR) pipeline. This method enforces strict semantic equivalence by integrating Unified Medical Language System (UMLS) Concept Unique Identifiers (CUIs) with micro-level entity constraints. MedLayBench-V provides a verified foundation for training and evaluating next-generation Med-VLMs capable of bridging the communication divide between clinical experts and patients.

Problem

• Medical Vision-Language Models
• lay language
• semantic alignment
• multimodal benchmark
• patient communication

Innovation

• expert-lay alignment
• medical vision-language models
• semantic equivalence
• UMLS CUIs
• multimodal benchmark