CURE: A Multimodal Benchmark for Clinical Understanding and Retrieval Evaluation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| 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 |