CURE: A Multimodal Benchmark for Clinical Understanding and Retrieval Evaluation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gu, Yannian, Huang, Zhongzhen, Mu, Linjie, Zhang, Xizhuo, Zhang, Shaoting, Zhang, Xiaofan
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918398817992704
author Gu, Yannian
Huang, Zhongzhen
Mu, Linjie
Zhang, Xizhuo
Zhang, Shaoting
Zhang, Xiaofan
author_facet Gu, Yannian
Huang, Zhongzhen
Mu, Linjie
Zhang, Xizhuo
Zhang, Shaoting
Zhang, Xiaofan
contents Multimodal large language models (MLLMs) demonstrate considerable potential in clinical diagnostics, a domain that inherently requires synthesizing complex visual and textual data alongside consulting authoritative medical literature. However, existing benchmarks primarily evaluate MLLMs in end-to-end answering scenarios. This limits the ability to disentangle a model's foundational multimodal reasoning from its proficiency in evidence retrieval and application. We introduce the Clinical Understanding and Retrieval Evaluation (CURE) benchmark. Comprising $500$ multimodal clinical cases mapped to physician-cited reference literature, CURE evaluates reasoning and retrieval under controlled evidence settings to disentangle their respective contributions. We evaluate state-of-the-art MLLMs across distinct evidence-gathering paradigms in both closed-ended and open-ended diagnosis tasks. Evaluations reveal a stark dichotomy: while advanced models demonstrate clinical reasoning proficiency when supplied with physician reference evidence (achieving up to $73.4\%$ accuracy on differential diagnosis), their performance substantially declines (as low as $25.4\%$) when reliant on independent retrieval mechanisms. This disparity highlights the dual challenges of effectively integrating multimodal clinical evidence and retrieving precise supporting literature. CURE is publicly available at https://github.com/yanniangu/CURE.
format Preprint
id arxiv_https___arxiv_org_abs_2603_19274
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle CURE: A Multimodal Benchmark for Clinical Understanding and Retrieval Evaluation
Gu, Yannian
Huang, Zhongzhen
Mu, Linjie
Zhang, Xizhuo
Zhang, Shaoting
Zhang, Xiaofan
Computation and Language
Artificial Intelligence
Multimodal large language models (MLLMs) demonstrate considerable potential in clinical diagnostics, a domain that inherently requires synthesizing complex visual and textual data alongside consulting authoritative medical literature. However, existing benchmarks primarily evaluate MLLMs in end-to-end answering scenarios. This limits the ability to disentangle a model's foundational multimodal reasoning from its proficiency in evidence retrieval and application. We introduce the Clinical Understanding and Retrieval Evaluation (CURE) benchmark. Comprising $500$ multimodal clinical cases mapped to physician-cited reference literature, CURE evaluates reasoning and retrieval under controlled evidence settings to disentangle their respective contributions. We evaluate state-of-the-art MLLMs across distinct evidence-gathering paradigms in both closed-ended and open-ended diagnosis tasks. Evaluations reveal a stark dichotomy: while advanced models demonstrate clinical reasoning proficiency when supplied with physician reference evidence (achieving up to $73.4\%$ accuracy on differential diagnosis), their performance substantially declines (as low as $25.4\%$) when reliant on independent retrieval mechanisms. This disparity highlights the dual challenges of effectively integrating multimodal clinical evidence and retrieving precise supporting literature. CURE is publicly available at https://github.com/yanniangu/CURE.
title CURE: A Multimodal Benchmark for Clinical Understanding and Retrieval Evaluation
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2603.19274