Lingshu：面向统一多模态医学理解与推理的通用基础模型

Computer Science > Computation and Language arXiv:2506.07044 (cs) [Submitted on 8 Jun 2025 (v1), last revised 21 Sep 2026 (this version, v5)] Title:Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning Authors:Weiwen Xu, Hou Pong Chan, Long Li, Mahani Aljunied, Ruifeng Yuan, Jianyu Wang, Chenghao Xiao, Guizhen Chen, Chaoqun Liu, Zhaodonghui Li, Yu Sun, Junao Shen, Chaojun Wang, Jie Tan, Deli Zhao, Tingyang Xu, Hao Zhang, Yu Rong View a PDF of the paper titled Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning, by Weiwen Xu and 17 other authors View PDF HTML (experimental) Abstract:Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in understanding common visual elements, largely due to their large-scale datasets and advanced training strategies. However, their effectiveness in medical applications remains limited due to the inherent discrepancies between data and tasks in medical scenarios and those in the general domain. Concretely, existing medical MLLMs face the following critical limitations: (1) limited coverage of medical knowledge beyond imaging, (2) heightened susceptibility to hallucinations due to suboptimal data curation processes, (3) lack of reasoning capabilities tailored for complex medical scenarios. To address these challenges, we first propose a comprehensive data curation procedure that (1) efficiently acquires rich medical knowledge data not only from medical imaging but also from extensive medical texts and general-domain data; and (2) synthesizes accurate medical captions, visual question answering (VQA), and reasoning samples. As a result, we build a multimodal dataset enriched with extensive medical knowledge. Building on the curated data, we introduce our medical-specialized MLLM: Lingshu. Lingshu undergoes multi-stage training to embed medical expertise and enhance its task-solving capabilities progressively. Besides, we preliminarily explore the potential of applying reinforcement learning with verifiable rewards paradigm to enhance Lingshu's medical reasoning ability. Additionally, we develop MedEvalKit, a unified evaluation framework that consolidates leading multimodal and textual medical benchmarks for standardized, fair, and efficient model assessment. We evaluate the performance of Lingshu on three fundamental medical tasks, multimodal QA, text-based QA, and medical report generation. The results show that Lingshu consistently outperforms the existing open-source multimodal models on most tasks ... Comments: Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV) Cite as: arXiv:2506.07044 [cs.CL] (or arXiv:2506.07044v5 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2506.07044 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Weiwen Xu [view email] [v1] Sun, 8 Jun 2025 08:47:30 UTC (5,004 KB) [v2] Tue, 10 Jun 2025 07:38:24 UTC (5,003 KB) [v3] Wed, 11 Jun 2025 09:12:18 UTC (4,851 KB) [v4] Fri, 13 Jun 2025 04:22:02 UTC (4,907 KB) [v5] Mon, 21 Sep 2026 13:27:01 UTC (5,652 KB) Full-text links: Access Paper: View a PDF of the paper titled Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning, by Weiwen Xu and 17 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CL new | recent | 2025-06 Change to browse by: cs cs.AI cs.CV References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)