{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:40:10Z","timestamp":1786120810308,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":124,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T00:00:00Z","timestamp":1786147200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770855.3817571","type":"proceedings-article","created":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:08:33Z","timestamp":1786064913000},"page":"10068-10079","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["EHRBench: An Automated and Reliable EHR-based Benchmark for Clinical Decision Making with LLMs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-3241-9418","authenticated-orcid":false,"given":"Yuzhang","family":"Xie","sequence":"first","affiliation":[{"name":"Emory University, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3969-3217","authenticated-orcid":false,"given":"Keqi","family":"Han","sequence":"additional","affiliation":[{"name":"Emory University, Atlanta, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5779-3531","authenticated-orcid":false,"given":"Yunpeng","family":"Xiao","sequence":"additional","affiliation":[{"name":"Emory University, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6388-2619","authenticated-orcid":false,"given":"Hejie","family":"Cui","sequence":"additional","affiliation":[{"name":"Stanford University, Stanford, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1295-5966","authenticated-orcid":false,"given":"Guanchen","family":"Wu","sequence":"additional","affiliation":[{"name":"Emory University, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4261-8733","authenticated-orcid":false,"given":"Ziyang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Emory University, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6043-1764","authenticated-orcid":false,"given":"Kai","family":"Shu","sequence":"additional","affiliation":[{"name":"Emory University, Atlanta, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9052-6951","authenticated-orcid":false,"given":"Jiaying","family":"Lu","sequence":"additional","affiliation":[{"name":"Emory University, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9478-5571","authenticated-orcid":false,"given":"Xiao","family":"Hu","sequence":"additional","affiliation":[{"name":"Emory University, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9145-4531","authenticated-orcid":false,"given":"Carl","family":"Yang","sequence":"additional","affiliation":[{"name":"Emory University, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Florencia Leoni Aleman, et al","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, et al., 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_2_1","volume-title":"Jakob Nikolas Kather, Daniel Truhn, and Keno Bressem.","author":"Adams Lisa","year":"2025","unstructured":"Lisa Adams, Felix Busch, Tianyu Han, Jean-Baptiste Excoffier, Matthieu Ortala, Alexander L\u00f6ser, Hugo JWL Aerts, Jakob Nikolas Kather, Daniel Truhn, and Keno Bressem. 2025. Longhealth: A question answering benchmark with long clinical documents. Journal of Healthcare Informatics Research (2025), 1-17."},{"key":"e_1_3_2_1_3_1","volume-title":"Preston Bowman, Joaquin Qui\u00f1onero-Candela, Foivos Tsimpourlas, et al.","author":"Arora Rahul K","year":"2025","unstructured":"Rahul K Arora, Jason Wei, Rebecca Soskin Hicks, Preston Bowman, Joaquin Qui\u00f1onero-Candela, Foivos Tsimpourlas, et al., 2025. Healthbench: Evaluating large language models towards improved human health. arXiv preprint arXiv:2505.08775 (2025)."},{"key":"e_1_3_2_1_4_1","volume-title":"V24, 1","author":"Artsi Yaara","year":"2024","unstructured":"Yaara Artsi, Vera Sorin, Eli Konen, Benjamin S Glicksberg, Girish Nadkarni, and Eyal Klang. 2024. Large language models for generating medical examinations: systematic review. BMC medical education, V24, 1 (2024), 354."},{"key":"e_1_3_2_1_5_1","volume-title":"Ehrxqa: A multi-modal question answering dataset for electronic health records with chest x-ray images. Advances in Neural Information Processing Systems, V36","author":"Bae Seongsu","year":"2023","unstructured":"Seongsu Bae, Daeun Kyung, Jaehee Ryu, Eunbyeol Cho, Gyubok Lee, Sunjun Kweon, et al., 2023. Ehrxqa: A multi-modal question answering dataset for electronic health records with chest x-ray images. Advances in Neural Information Processing Systems, V36 (2023), 3867-3880."},{"key":"e_1_3_2_1_6_1","volume-title":"Anton Lozhkov, Nouamane Tazi, Lewis Tunstall, Carlos Miguel Patino, et al.","author":"Bakouch Elie","year":"2025","unstructured":"Elie Bakouch, Loubna Ben Allal, Anton Lozhkov, Nouamane Tazi, Lewis Tunstall, Carlos Miguel Patino, et al., 2025. SmolLM3: smol, multilingual, long-context reasoner. Hugging Face Blog (2025)."},{"key":"e_1_3_2_1_7_1","volume-title":"Drugehrqa: A question answering dataset on structured and unstructured electronic health records for medicine related queries. arXiv preprint arXiv:2205.01290","author":"Bardhan Jayetri","year":"2022","unstructured":"Jayetri Bardhan, Anthony Colas, Kirk Roberts, and Daisy Zhe Wang. 2022. Drugehrqa: A question answering dataset on structured and unstructured electronic health records for medicine related queries. arXiv preprint arXiv:2205.01290 (2022)."},{"key":"e_1_3_2_1_8_1","volume-title":"V8, 1","author":"Bhasuran Balu","year":"2025","unstructured":"Balu Bhasuran, Qiao Jin, Yuzhang Xie, Carl Yang, Karim Hanna, Jennifer Costa, Cindy Shavor, Wenshan Han, Zhiyong Lu, and Zhe He. 2025. Preliminary analysis of the impact of lab results on large language model generated differential diagnoses. npj Digital Medicine, V8, 1 (2025), 166."},{"key":"e_1_3_2_1_9_1","volume-title":"V32, suppl_1","author":"Bodenreider Olivier","year":"2004","unstructured":"Olivier Bodenreider. 2004. The unified medical language system (UMLS): integrating biomedical terminology. Nucleic acids research, V32, suppl_1 (2004), D267-D270."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Joeran S Bosma Koen Dercksen Luc Builtjes Romain Andr\u00e9 Christian Roest Stefan J Fransen Constant R Noordman Mar Navarro-Padilla Judith Lefkes Nat\u00e1lia Alves et al. 2025. The DRAGON benchmark for clinical NLP. npj Digital Medicine V8 1 (2025) 289.","DOI":"10.1038\/s41746-025-01626-x"},{"key":"e_1_3_2_1_11_1","volume-title":"V2, 1","author":"Canese Kathi","year":"2013","unstructured":"Kathi Canese and Sarah Weis. 2013. PubMed: the bibliographic database. The NCBI handbook, V2, 1 (2013), 2013."},{"key":"e_1_3_2_1_12_1","volume-title":"towards medical complex reasoning with llms. arXiv preprint arXiv:2412.18925","author":"Chen Junying","year":"2024","unstructured":"Junying Chen, Zhenyang Cai, Ke Ji, Xidong Wang, Wanlong Liu, Rongsheng Wang, Jianye Hou, and Benyou Wang. 2024. Huatuogpt-o1, towards medical complex reasoning with llms. arXiv preprint arXiv:2412.18925 (2024)."},{"key":"e_1_3_2_1_13_1","volume-title":"Simulating Viva Voce Examinations to Evaluate Clinical Reasoning in Large Language Models. arXiv preprint arXiv:2510.10278","author":"Chiu Christopher","year":"2025","unstructured":"Christopher Chiu, Silviu Pitis, and Mihaela van der Schaar. 2025. Simulating Viva Voce Examinations to Evaluate Clinical Reasoning in Large Language Models. arXiv preprint arXiv:2510.10278 (2025)."},{"key":"e_1_3_2_1_14_1","unstructured":"Cl\u00e9ment Christophe Praveen K Kanithi Tathagata Raha Shadab Khan and Marco AF Pimentel. 2024. Med42-v2: A Suite of Clinical LLMs. https:\/\/arxiv.org\/abs\/2408.06142"},{"key":"e_1_3_2_1_15_1","volume-title":"Emily Alsentzer, Sanmi Koyejo, and Nigam H Shah.","author":"Cui Hejie","year":"2025","unstructured":"Hejie Cui, Alyssa Unell, Bowen Chen, Jason Alan Fries, Emily Alsentzer, Sanmi Koyejo, and Nigam H Shah. 2025. Timer: Temporal instruction modeling and evaluation for longitudinal clinical records. npj Digital Medicine, V8, 1 (2025), 577."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.cl4health-1.10"},{"key":"e_1_3_2_1_17_1","volume-title":"Climb: Data foundations for large scale multimodal clinical foundation models. arXiv preprint arXiv:2503.07667","author":"Dai Wei","year":"2025","unstructured":"Wei Dai, Peilin Chen, Malinda Lu, Daniel Li, Haowen Wei, Hejie Cui, and Paul Pu Liang. 2025. Climb: Data foundations for large scale multimodal clinical foundation models. arXiv preprint arXiv:2503.07667 (2025)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocaf045"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-naacl.3"},{"key":"e_1_3_2_1_20_1","volume-title":"Proceedings of the 31st International Conference on Computational Linguistics. 10183-10213","author":"Fan Zhihao","year":"2025","unstructured":"Zhihao Fan, Lai Wei, Jialong Tang, Wei Chen, Wang Siyuan, Zhongyu Wei, and Fei Huang. 2025b. Ai hospital: Benchmarking large language models in a multi-agent medical interaction simulator. In Proceedings of the 31st International Conference on Computational Linguistics. 10183-10213."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i20.30205"},{"key":"e_1_3_2_1_22_1","volume-title":"Chatglm: A family of large language models from glm-130b to glm-4 all tools. arXiv preprint arXiv:2406.12793","author":"Glm Team","year":"2024","unstructured":"Team Glm, Aohan Zeng, Bin Xu, Bowen Wang, Chenhui Zhang, Da Yin, et al., 2024. Chatglm: A family of large language models from glm-130b to glm-4 all tools. arXiv preprint arXiv:2406.12793 (2024)."},{"key":"e_1_3_2_1_23_1","volume-title":"The Dialogue That Heals: A Comprehensive Evaluation of Doctor Agents' Inquiry Capability. arXiv preprint arXiv:2509.24958","author":"Gong Linlu","year":"2025","unstructured":"Linlu Gong, Ante Wang, Yunghwei Lai, Weizhi Ma, and Yang Liu. 2025. The Dialogue That Heals: A Comprehensive Evaluation of Doctor Agents' Inquiry Capability. arXiv preprint arXiv:2509.24958 (2025)."},{"key":"e_1_3_2_1_24_1","unstructured":"Aaron Grattafiori Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle et al. 2024. The llama 3 herd of models. arXiv preprint arXiv:2407.21783 (2024)."},{"key":"e_1_3_2_1_25_1","volume-title":"Chbench: A chinese dataset for evaluating health in large language models. arXiv preprint arXiv:2409.15766","author":"Guo Chenlu","year":"2024","unstructured":"Chenlu Guo, Nuo Xu, Yi Chang, and Yuan Wu. 2024. Chbench: A chinese dataset for evaluating health in large language models. arXiv preprint arXiv:2409.15766 (2024)."},{"key":"e_1_3_2_1_26_1","volume-title":"Towards a Virtual Neuroscientist: Autonomous Neuroimaging Analysis via Multi-Agent Collaboration. arXiv preprint arXiv:2605.09366","author":"Han Keqi","year":"2026","unstructured":"Keqi Han, Songlin Zhao, Yao Su, Xiang Li, Yixuan Yuan, Lifang He, and Carl Yang. 2026. Towards a Virtual Neuroscientist: Autonomous Neuroimaging Analysis via Multi-Agent Collaboration. arXiv preprint arXiv:2605.09366 (2026)."},{"key":"e_1_3_2_1_27_1","volume-title":"Medsafetybench: Evaluating and improving the medical safety of large language models. Advances in Neural Information Processing Systems, V37","author":"Han Tessa","year":"2024","unstructured":"Tessa Han, Aounon Kumar, Chirag Agarwal, and Himabindu Lakkaraju. 2024. Medsafetybench: Evaluating and improving the medical safety of large language models. Advances in Neural Information Processing Systems, V37 (2024), 33423-33454."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1097\/ACM.0000000000003707"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02093"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Lei Huang Weijiang Yu Weitao Ma Weihong Zhong Zhangyin Feng Haotian Wang et al. 2025b. A survey on hallucination in large language models: Principles taxonomy challenges and open questions. ACM Transactions on Information Systems V43 2 (2025) 1-55.","DOI":"10.1145\/3703155"},{"key":"e_1_3_2_1_31_1","volume-title":"m1: Unleash the potential of test-time scaling for medical reasoning with large language models. arXiv preprint arXiv:2504.00869","author":"Huang Xiaoke","year":"2025","unstructured":"Xiaoke Huang, Juncheng Wu, Hui Liu, Xianfeng Tang, and Yuyin Zhou. 2025a. m1: Unleash the potential of test-time scaling for medical reasoning with large language models. arXiv preprint arXiv:2504.00869 (2025)."},{"key":"e_1_3_2_1_32_1","volume-title":"Ralph TH Leijenaar, Jochen WL Cals, Annemarie A Uijen, and Henk J Schers.","author":"Hunik Liesbeth","year":"2025","unstructured":"Liesbeth Hunik, Asma Chaabouni, Twan van Laarhoven, Tim C Olde Hartman, Ralph TH Leijenaar, Jochen WL Cals, Annemarie A Uijen, and Henk J Schers. 2025. Diagnostic Prediction Models for Primary Care, Based on AI and Electronic Health Records: Systematic Review. JMIR Medical Informatics, V13, 1 (2025), e62862."},{"key":"e_1_3_2_1_33_1","volume-title":"Proceedings of the 31st International Conference on Computational Linguistics. 9278-9298","author":"Jia Mingyi","year":"2025","unstructured":"Mingyi Jia, Junwen Duan, Yan Song, and Jianxin Wang. 2025. medikal: Integrating knowledge graphs as assistants of llms for enhanced clinical diagnosis on emrs. In Proceedings of the 31st International Conference on Computational Linguistics. 9278-9298."},{"key":"e_1_3_2_1_34_1","unstructured":"AQ Jiang A Sablayrolles A Mensch C Bamford DS Chaplot D de Las Casas et al. 2023. Mistral 7B. arXiv 2023. arXiv preprint arXiv:2310.06825 (2023)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.3390\/app11146421"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"crossref","unstructured":"Alistair EW Johnson Lucas Bulgarelli Lu Shen Alvin Gayles Ayad Shammout Steven Horng Tom J Pollard Sicheng Hao Benjamin Moody Brian Gow et al. 2023. MIMIC-IV a freely accessible electronic health record dataset. Scientific data V10 1 (2023) 1.","DOI":"10.1038\/s41597-022-01899-x"},{"key":"e_1_3_2_1_37_1","volume-title":"Leo Anthony Celi, and Roger G Mark","author":"Johnson Alistair EW","year":"2016","unstructured":"Alistair EW Johnson, Tom J Pollard, Lu Shen, Li-wei H Lehman, Mengling Feng, Mohammad Ghassemi, Benjamin Moody, Peter Szolovits, Leo Anthony Celi, and Roger G Mark. 2016. MIMIC-III, a freely accessible critical care database. Scientific data, V3, 1 (2016), 1-9."},{"key":"e_1_3_2_1_38_1","volume-title":"AAAI 2024 Spring Symposium on Clinical Foundation Models.","author":"Johri Shreya","year":"2024","unstructured":"Shreya Johri, Jaehwan Jeong, Benjamin A Tran, Daniel I Schlessinger, Shannon Wongvibulsin, Zhuo Ran Cai, Roxana Daneshjou, and Pranav Rajpurkar. 2024. CRAFT-MD: A conversational evaluation framework for comprehensive assessment of clinical LLMs. In AAAI 2024 Spring Symposium on Clinical Foundation Models."},{"key":"e_1_3_2_1_39_1","volume-title":"Medcalc-bench: Evaluating large language models for medical calculations. Advances in Neural Information Processing Systems, V37","author":"Khandekar Nikhil","year":"2024","unstructured":"Nikhil Khandekar, Qiao Jin, Guangzhi Xiong, Soren Dunn, Serina Applebaum, Zain Anwar, Maame Sarfo-Gyamfi, Conrad Safranek, Abid Anwar, Andrew Zhang, et al., 2024. Medcalc-bench: Evaluating large language models for medical calculations. Advances in Neural Information Processing Systems, V37 (2024), 84730-84745."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/bts591"},{"key":"e_1_3_2_1_41_1","volume-title":"V18, 2","author":"Kim Michelle Kang","year":"2023","unstructured":"Michelle Kang Kim, Carol Rouphael, John McMichael, Nicole Welch, and Srinivasan Dasarathy. 2023. Challenges in and opportunities for electronic health record-based data analysis and interpretation. Gut and liver, V18, 2 (2023), 201."},{"key":"e_1_3_2_1_42_1","volume-title":"MedExQA: Medical question answering benchmark with multiple explanations. arXiv preprint arXiv:2406.06331","author":"Kim Yunsoo","year":"2024","unstructured":"Yunsoo Kim, Jinge Wu, Yusuf Abdulle, and Honghan Wu. 2024. MedExQA: Medical question answering benchmark with multiple explanations. arXiv preprint arXiv:2406.06331 (2024)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1136\/ard-2022-222626"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12652-021-03612-z"},{"key":"e_1_3_2_1_45_1","volume-title":"Ehrnoteqa: An llm benchmark for real-world clinical practice using discharge summaries. Advances in Neural Information Processing Systems, V37","author":"Kweon Sunjun","year":"2024","unstructured":"Sunjun Kweon, Jiyoun Kim, Heeyoung Kwak, Dongchul Cha, Hangyul Yoon, Kwang Kim, Jeewon Yang, Seunghyun Won, and Edward Choi. 2024. Ehrnoteqa: An llm benchmark for real-world clinical practice using discharge summaries. Advances in Neural Information Processing Systems, V37 (2024), 124575-124611."},{"key":"e_1_3_2_1_46_1","volume-title":"Doctor-r1: Mastering clinical inquiry with experiential agentic reinforcement learning. arXiv preprint arXiv:2510.04284","author":"Lai Yunghwei","year":"2025","unstructured":"Yunghwei Lai, Kaiming Liu, Ziyue Wang, Weizhi Ma, and Yang Liu. 2025. Doctor-r1: Mastering clinical inquiry with experiential agentic reinforcement learning. arXiv preprint arXiv:2510.04284 (2025)."},{"key":"e_1_3_2_1_47_1","volume-title":"Ehrsql: A practical text-to-sql benchmark for electronic health records. Advances in Neural Information Processing Systems, V35","author":"Lee Gyubok","year":"2022","unstructured":"Gyubok Lee, Hyeonji Hwang, Seongsu Bae, Yeonsu Kwon, Woncheol Shin, Seongjun Yang, Minjoon Seo, Jong-Yeup Kim, and Edward Choi. 2022. Ehrsql: A practical text-to-sql benchmark for electronic health records. Advances in Neural Information Processing Systems, V35 (2022), 15589-15601."},{"key":"e_1_3_2_1_48_1","unstructured":"Junkai Li Yunghwei Lai Weitao Li Jingyi Ren Meng Zhang Xinhui Kang Siyu Wang Peng Li Ya-Qin Zhang Weizhi Ma et al. 2024b. Agent hospital: A simulacrum of hospital with evolvable medical agents. arXiv preprint arXiv:2405.02957 (2024)."},{"key":"e_1_3_2_1_49_1","volume-title":"Pang Wei W Koh, and Yulia Tsvetkov","author":"Li Stella","year":"2024","unstructured":"Stella Li, Vidhisha Balachandran, Shangbin Feng, Jonathan Ilgen, Emma Pierson, Pang Wei W Koh, and Yulia Tsvetkov. 2024a. Mediq: Question-asking llms and a benchmark for reliable interactive clinical reasoning. Advances in Neural Information Processing Systems, V37 (2024), 28858-28888."},{"key":"e_1_3_2_1_50_1","unstructured":"Yusheng Liao Chaoyi Wu Junwei Liu Shuyang Jiang Pengcheng Qiu Haowen Wang Yun Yue Shuai Zhen Jian Wang Qianrui Fan et al. 2025. EHR-R1: A Reasoning-Enhanced Foundational Language Model for Electronic Health Record Analysis. arXiv preprint arXiv:2510.25628 (2025)."},{"key":"e_1_3_2_1_51_1","unstructured":"Alexander H Liu Kartik Khandelwal Sandeep Subramanian Victor Jouault Abhinav Rastogi Adrien Sad\u00e9 et al. 2026. Ministral 3. arXiv preprint arXiv:2601.08584 (2026)."},{"key":"e_1_3_2_1_52_1","unstructured":"Fenglin Liu Zheng Li Hongjian Zhou Qingyu Yin Jingfeng Yang Xianfeng Tang Chen Luo Ming Zeng Haoming Jiang Yifan Gao et al. 2024a. Large language models in the clinic: a comprehensive benchmark. arXiv preprint arXiv:2405.00716 (2024)."},{"key":"e_1_3_2_1_53_1","volume-title":"RiskAgent: Autonomous Medical AI Copilot for Generalist Risk Prediction. arXiv preprint arXiv:2503.03802","author":"Liu Fenglin","year":"2025","unstructured":"Fenglin Liu, Jinge Wu, Hongjian Zhou, Xiao Gu, Soheila Molaei, Anshul Thakur, Lei Clifton, Honghan Wu, and David A Clifton. 2025b. RiskAgent: Autonomous Medical AI Copilot for Generalist Risk Prediction. arXiv preprint arXiv:2503.03802 (2025)."},{"key":"e_1_3_2_1_54_1","volume-title":"Medchain: Bridging the gap between llm agents and clinical practice through interactive sequential benchmarking. arXiv preprint arXiv:2412.01605","author":"Liu Jie","year":"2024","unstructured":"Jie Liu, Wenxuan Wang, Zizhan Ma, Guolin Huang, Yihang SU, Kao-Jung Chang, Wenting Chen, Haoliang Li, Linlin Shen, and Michael Lyu. 2024b. Medchain: Bridging the gap between llm agents and clinical practice through interactive sequential benchmarking. arXiv preprint arXiv:2412.01605 (2024)."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.1178"},{"key":"e_1_3_2_1_56_1","volume-title":"Proceedings of the 31st International Conference on Computational Linguistics. 4871-4896","author":"Liu Ruoyu","year":"2025","unstructured":"Ruoyu Liu, Kui Xue, Xiaofan Zhang, and Shaoting Zhang. 2025c. Interactive evaluation for medical llms via task-oriented dialogue system. In Proceedings of the 31st International Conference on Computational Linguistics. 4871-4896."},{"key":"e_1_3_2_1_57_1","volume-title":"On llms-driven synthetic data generation, curation, and evaluation: A survey. arXiv preprint arXiv:2406.15126","author":"Long Lin","year":"2024","unstructured":"Lin Long, Rui Wang, Ruixuan Xiao, Junbo Zhao, Xiao Ding, Gang Chen, and Haobo Wang. 2024. On llms-driven synthetic data generation, curation, and evaluation: A survey. arXiv preprint arXiv:2406.15126 (2024)."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.718"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.167"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.5455\/aim.2022.30.230-235"},{"key":"e_1_3_2_1_61_1","volume-title":"ER-REASON: A Benchmark Dataset for LLM-Based Clinical Reasoning in the Emergency Room. arXiv preprint arXiv:2505.22919","author":"Mehandru Nikita","year":"2025","unstructured":"Nikita Mehandru, Niloufar Golchini, David Bamman, Travis Zack, Melanie F Molina, and Ahmed Alaa. 2025. ER-REASON: A Benchmark Dataset for LLM-Based Clinical Reasoning in the Emergency Room. arXiv preprint arXiv:2505.22919 (2025)."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13326-024-00306-1"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.585"},{"key":"e_1_3_2_1_64_1","volume-title":"Marc Wilson, Xiaoxuan Liu, Viknesh Sounderajah, Jonathan Carlson, Matthew P Lungren, et al.","author":"Nori Harsha","year":"2025","unstructured":"Harsha Nori, Mayank Daswani, Christopher Kelly, Scott Lundberg, Marco Tulio Ribeiro, Marc Wilson, Xiaoxuan Liu, Viknesh Sounderajah, Jonathan Carlson, Matthew P Lungren, et al., 2025. Sequential Diagnosis with Language Models. arXiv preprint arXiv:2506.22405 (2025)."},{"key":"e_1_3_2_1_65_1","volume-title":"John F Hurdle, and Carol M Ashton.","author":"O'malley Kimberly J","year":"2005","unstructured":"Kimberly J O'malley, Karon F Cook, Matt D Price, Kimberly Raiford Wildes, John F Hurdle, and Carol M Ashton. 2005. Measuring diagnoses: ICD code accuracy. Health services research, V40, 5p2 (2005), 1620-1639."},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICHI61247.2024.00111"},{"key":"e_1_3_2_1_67_1","volume-title":"Conference on health, inference, and learning. PMLR, 248-260","author":"Pal Ankit","year":"2022","unstructured":"Ankit Pal, Logesh Kumar Umapathi, and Malaikannan Sankarasubbu. 2022. Medmcqa: A large-scale multi-subject multi-choice dataset for medical domain question answering. In Conference on health, inference, and learning. PMLR, 248-260."},{"key":"e_1_3_2_1_68_1","volume-title":"emrqa: A large corpus for question answering on electronic medical records. arXiv preprint arXiv:1809.00732","author":"Pampari Anusri","year":"2018","unstructured":"Anusri Pampari, Preethi Raghavan, Jennifer Liang, and Jian Peng. 2018. emrqa: A large corpus for question answering on electronic medical records. arXiv preprint arXiv:1809.00732 (2018)."},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"crossref","unstructured":"Maria Panagioti Kanza Khan Richard N Keers Aseel Abuzour Denham Phipps Evangelos Kontopantelis Peter Bower Stephen Campbell Razaan Haneef Anthony J Avery et al. 2019. Prevalence severity and nature of preventable patient harm across medical care settings: systematic review and meta-analysis. bmj V366 (2019).","DOI":"10.1136\/bmj.l4185"},{"key":"e_1_3_2_1_70_1","volume-title":"Machine Learning for Healthcare Conference. PMLR, 36-53","author":"Park Junwoo","year":"2021","unstructured":"Junwoo Park, Youngwoo Cho, Haneol Lee, Jaegul Choo, and Edward Choi. 2021. Knowledge graph-based question answering with electronic health records. In Machine Learning for Healthcare Conference. PMLR, 36-53."},{"key":"e_1_3_2_1_71_1","volume-title":"A Novel Approach to Study Medical Decision Making in the Clinical Setting: The ''Own-point-of-view'' Perspective","author":"Pelaccia Thierry","year":"2017","unstructured":"Thierry Pelaccia, Jacques Tardif, Emmanuel Triby, and Bernard Charlin. 2017. A Novel Approach to Study Medical Decision Making in the Clinical Setting: The ''Own-point-of-view'' Perspective. Academic Emergency Medicine, V24, 7 (2017), 785-795."},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i27.35050"},{"key":"e_1_3_2_1_73_1","volume-title":"Quantifying the reasoning abilities of llms on real-world clinical cases. arXiv preprint arXiv:2503.04691","author":"Qiu Pengcheng","year":"2025","unstructured":"Pengcheng Qiu, Chaoyi Wu, Shuyu Liu, Weike Zhao, Zhuoxia Chen, Hongfei Gu, Chuanjin Peng, Ya Zhang, Yanfeng Wang, and Weidi Xie. 2025. Quantifying the reasoning abilities of llms on real-world clinical cases. arXiv preprint arXiv:2503.04691 (2025)."},{"key":"e_1_3_2_1_74_1","volume-title":"emrkbqa: A clinical knowledge-base question answering dataset","author":"Raghavan Preethi","unstructured":"Preethi Raghavan, Jennifer J Liang, Diwakar Mahajan, Rachita Chandra, and Peter Szolovits. 2021. emrkbqa: A clinical knowledge-base question answering dataset. Association for Computational Linguistics."},{"key":"e_1_3_2_1_75_1","volume-title":"AgentClinic: a multimodal agent benchmark to evaluate AI in simulated clinical environments. arXiv preprint arXiv:2405.07960","author":"Schmidgall Samuel","year":"2024","unstructured":"Samuel Schmidgall, Rojin Ziaei, Carl Harris, Eduardo Reis, Jeffrey Jopling, and Michael Moor. 2024. AgentClinic: a multimodal agent benchmark to evaluate AI in simulated clinical environments. arXiv preprint arXiv:2405.07960 (2024)."},{"key":"e_1_3_2_1_76_1","volume-title":"LLM-MINE: Large Language Model based Alzheimer's Disease and Related Dementias Phenotypes Mining from Clinical Notes. arXiv preprint arXiv:2603.13673","author":"Shao Mingchen","year":"2026","unstructured":"Mingchen Shao, Yuzhang Xie, Carl Yang, and Jiaying Lu. 2026. LLM-MINE: Large Language Model based Alzheimer's Disease and Related Dementias Phenotypes Mining from Clinical Notes. arXiv preprint arXiv:2603.13673 (2026)."},{"key":"e_1_3_2_1_77_1","volume-title":"V182","author":"Shoham Ofir Ben","year":"2024","unstructured":"Ofir Ben Shoham and Nadav Rappoport. 2024. MedConceptsQA: Open source medical concepts QA benchmark. Computers in Biology and Medicine, V182 (2024), 109089."},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.63317\/375gmipk72qh"},{"key":"e_1_3_2_1_79_1","unstructured":"Aaditya Singh Adam Fry Adam Perelman Adam Tart Adi Ganesh Ahmed El-Kishky et al. 2025. Openai gpt-5 system card. arXiv preprint arXiv:2601.03267 (2025)."},{"key":"e_1_3_2_1_80_1","volume-title":"Nathan Scales, Ajay Tanwani, Heather Cole-Lewis, Stephen Pfohl, et al.","author":"Singhal Karan","year":"2023","unstructured":"Karan Singhal, Shekoofeh Azizi, Tao Tu, S Sara Mahdavi, Jason Wei, Hyung Won Chung, Nathan Scales, Ajay Tanwani, Heather Cole-Lewis, Stephen Pfohl, et al., 2023. Large language models encode clinical knowledge. Nature, V620, 7972 (2023), 172-180."},{"key":"e_1_3_2_1_81_1","volume-title":"V29, 1","author":"Subbiah Vivek","year":"2023","unstructured":"Vivek Subbiah. 2023. The next generation of evidence-based medicine. Nature medicine, V29, 1 (2023), 49-58."},{"key":"e_1_3_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.1344"},{"key":"e_1_3_2_1_83_1","unstructured":"Tao Tu Mike Schaekermann Anil Palepu Khaled Saab Jan Freyberg Ryutaro Tanno Amy Wang Brenna Li Mohamed Amin Yong Cheng et al. 2025. Towards conversational diagnostic artificial intelligence. Nature (2025) 1-9."},{"key":"e_1_3_2_1_84_1","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2021.1276"},{"key":"e_1_3_2_1_85_1","doi-asserted-by":"publisher","DOI":"10.1145\/3535508.3545518"},{"key":"e_1_3_2_1_86_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380120"},{"key":"e_1_3_2_1_87_1","volume-title":"BioMedJImpact: A Comprehensive Dataset and LLM Pipeline for AI Engagement and Scientific Impact Analysis of Biomedical Journals. arXiv preprint arXiv:2511.12821","author":"Wang Ruiyu","year":"2025","unstructured":"Ruiyu Wang, Yuzhang Xie, Xiao Hu, Carl Yang, and Jiaying Lu. 2025b. BioMedJImpact: A Comprehensive Dataset and LLM Pipeline for AI Engagement and Scientific Impact Analysis of Biomedical Journals. arXiv preprint arXiv:2511.12821 (2025)."},{"key":"e_1_3_2_1_88_1","doi-asserted-by":"publisher","DOI":"10.36227\/techrxiv.177092226.67693184\/v1"},{"key":"e_1_3_2_1_89_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.343"},{"key":"e_1_3_2_1_90_1","volume-title":"Apollo: A lightweight multilingual medical LLM towards democratizing medical AI to 6B people. arXiv preprint arXiv:2403.03640","author":"Wang Xidong","year":"2024","unstructured":"Xidong Wang, Nuo Chen, Junyin Chen, Yidong Wang, Guorui Zhen, Chunxian Zhang, Xiangbo Wu, Yan Hu, Anningzhe Gao, Xiang Wan, et al., 2024a. Apollo: A lightweight multilingual medical LLM towards democratizing medical AI to 6B people. arXiv preprint arXiv:2403.03640 (2024)."},{"key":"e_1_3_2_1_91_1","volume-title":"SE-Diff: Simulator and Experience Enhanced Diffusion Model for Comprehensive ECG Generation. In The Fourteenth International Conference on Learning Representations.","author":"Wang Xiaoda","year":"2026","unstructured":"Xiaoda Wang, Kaiqiao Han, Yuhao Xu, Xiao Luo, Yizhou Sun, Wei Wang, and Carl Yang. 2026 b. SE-Diff: Simulator and Experience Enhanced Diffusion Model for Comprehensive ECG Generation. In The Fourteenth International Conference on Learning Representations."},{"key":"e_1_3_2_1_92_1","volume-title":"TrialPanorama: Database and Benchmark for Systematic Review and Design of Clinical Trials. arXiv preprint arXiv:2505.16097","author":"Wang Zifeng","year":"2025","unstructured":"Zifeng Wang, Qiao Jin, Jiacheng Lin, Junyi Gao, Jathurshan Pradeepkumar, Pengcheng Jiang, Benjamin Danek, Zhiyong Lu, and Jimeng Sun. 2025a. TrialPanorama: Database and Benchmark for Systematic Review and Design of Clinical Trials. arXiv preprint arXiv:2505.16097 (2025)."},{"key":"e_1_3_2_1_93_1","volume-title":"Qi He, Lu Cheng, et al.","author":"Wei Mingyang","year":"2026","unstructured":"Mingyang Wei, Dehai Min, Zewen Liu, Yuzhang Xie, Guanchen Wu, Ziyang Zhang, Carl Yang, Max SY Lau, Qi He, Lu Cheng, et al., 2026. EpiQAL: Benchmarking Large Language Models in Epidemiological Question Answering for Enhanced Alignment and Reasoning. arXiv preprint arXiv:2601.03471 (2026)."},{"key":"e_1_3_2_1_94_1","volume-title":"Dean Cheng, Savita Shrivastava, Dan Tzur, Bijaya Gautam, and Murtaza Hassanali.","author":"Wishart David S","year":"2008","unstructured":"David S Wishart, Craig Knox, An Chi Guo, Dean Cheng, Savita Shrivastava, Dan Tzur, Bijaya Gautam, and Murtaza Hassanali. 2008. DrugBank: a knowledgebase for drugs, drug actions and drug targets. Nucleic acids research, V36, suppl_1 (2008), D901-D906."},{"key":"e_1_3_2_1_95_1","volume-title":"Ehrshot: An ehr benchmark for few-shot evaluation of foundation models. Advances in Neural Information Processing Systems, V36","author":"Wornow Michael","year":"2023","unstructured":"Michael Wornow, Rahul Thapa, Ethan Steinberg, Jason Fries, and Nigam Shah. 2023. Ehrshot: An ehr benchmark for few-shot evaluation of foundation models. Advances in Neural Information Processing Systems, V36 (2023), 67125-67137."},{"key":"e_1_3_2_1_96_1","volume-title":"V8, 1","author":"Wu Chaoyi","year":"2025","unstructured":"Chaoyi Wu, Pengcheng Qiu, Jinxin Liu, Hongfei Gu, Na Li, Ya Zhang, Yanfeng Wang, and Weidi Xie. 2025b. Towards evaluating and building versatile large language models for medicine. npj Digital Medicine, V8, 1 (2025), 58."},{"key":"e_1_3_2_1_97_1","volume-title":"Utilizing Large Language Models for Zero-Shot Medical Ontology Extension from Clinical Notes. arXiv preprint arXiv:2511.16548","author":"Wu Guanchen","year":"2025","unstructured":"Guanchen Wu, Yuzhang Xie, Huanwei Wu, Zhe He, Hui Shao, Xiao Hu, and Carl Yang. 2025c. Utilizing Large Language Models for Zero-Shot Medical Ontology Extension from Clinical Notes. arXiv preprint arXiv:2511.16548 (2025)."},{"key":"e_1_3_2_1_98_1","doi-asserted-by":"publisher","DOI":"10.1161\/str.56.suppl_1.TMP102"},{"key":"e_1_3_2_1_99_1","volume-title":"Beyond MedQA: Towards Real-world Clinical Decision Making in the Era of LLMs. arXiv preprint arXiv:2510.20001","author":"Xiao Yunpeng","year":"2025","unstructured":"Yunpeng Xiao, Carl Yang, Mark Mai, Xiao Hu, and Kai Shu. 2025. Beyond MedQA: Towards Real-world Clinical Decision Making in the Era of LLMs. arXiv preprint arXiv:2510.20001 (2025)."},{"key":"e_1_3_2_1_100_1","volume-title":"KERAP: A Knowledge-Enhanced Reasoning Approach for Accurate Zero-shot Diagnosis Prediction Using Multi-agent LLMs. arXiv preprint arXiv:2507.02773","author":"Xie Yuzhang","year":"2025","unstructured":"Yuzhang Xie, Hejie Cui, Ziyang Zhang, Jiaying Lu, Kai Shu, Fadi Nahab, Xiao Hu, and Carl Yang. 2025a. KERAP: A Knowledge-Enhanced Reasoning Approach for Accurate Zero-shot Diagnosis Prediction Using Multi-agent LLMs. arXiv preprint arXiv:2507.02773 (2025)."},{"key":"e_1_3_2_1_101_1","volume-title":"HypKG: Hypergraph-Based Knowledge Graph Contextualization for Precision Healthcare. In International Semantic Web Conference. Springer, 328-348","author":"Xie Yuzhang","year":"2025","unstructured":"Yuzhang Xie, Xu Han, Ran Xu, Xiao Hu, Jiaying Lu, and Carl Yang. 2025b. HypKG: Hypergraph-Based Knowledge Graph Contextualization for Precision Healthcare. In International Semantic Web Conference. Springer, 328-348."},{"key":"e_1_3_2_1_102_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657904"},{"key":"e_1_3_2_1_103_1","doi-asserted-by":"publisher","DOI":"10.1161\/str.56.suppl_1.WP175"},{"key":"e_1_3_2_1_104_1","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM55620.2022.9995480"},{"key":"e_1_3_2_1_105_1","doi-asserted-by":"crossref","unstructured":"Yuzhang Xie Qingqing Sang Qian Da Guoshuai Niu Shijie Deng Haoran Feng Yunqin Chen Yuan-Yuan Li Bingya Liu Yang Yang et al. 2024b. Improving diagnosis and outcome prediction of gastric cancer via multimodal learning using whole slide pathological images and gene expression. Artificial intelligence in medicine V152 (2024) 102871.","DOI":"10.1016\/j.artmed.2024.102871"},{"key":"e_1_3_2_1_106_1","volume-title":"Enhanced Atrial Fibrillation Prediction in ESUS Patients with Hypergraph-based Pre-training. arXiv preprint arXiv:2603.13297","author":"Xie Yuzhang","year":"2026","unstructured":"Yuzhang Xie, Yuhua Wu, Ruiyu Wang, Fadi Nahab, Xiao Hu, and Carl Yang. 2026. Enhanced Atrial Fibrillation Prediction in ESUS Patients with Hypergraph-based Pre-training. arXiv preprint arXiv:2603.13297 (2026)."},{"key":"e_1_3_2_1_107_1","volume-title":"The Second Workshop on GenAI for Health: Potential, Trust, and Policy Compliance.","author":"Xu Ran","year":"2025","unstructured":"Ran Xu, Yuchen Zhuang, Yishan Zhong, Yue Yu, Xiangru Tang, Hang Wu, May Dongmei Wang, Peifeng Ruan, Donghan Yang, Tao Wang, et al., 2025. Medagentgym: Training llm agents for code-based medical reasoning at scale. In The Second Workshop on GenAI for Health: Potential, Trust, and Policy Compliance."},{"key":"e_1_3_2_1_108_1","volume-title":"Cheng Fei, Benji Peng, Ziqian Bi, Pohsun Feng, Keyu Chen, et al.","author":"Yan Lawrence KQ","year":"2024","unstructured":"Lawrence KQ Yan, Qian Niu, Ming Li, Yichao Zhang, Caitlyn Heqi Yin, Cheng Fei, Benji Peng, Ziqian Bi, Pohsun Feng, Keyu Chen, et al., 2024. Large language model benchmarks in medical tasks. arXiv preprint arXiv:2410.21348 (2024)."},{"key":"e_1_3_2_1_109_1","unstructured":"An Yang Anfeng Li Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chang Gao Chengen Huang Chenxu Lv et al. 2025. Qwen3 technical report. arXiv preprint arXiv:2505.09388 (2025)."},{"key":"e_1_3_2_1_110_1","unstructured":"An Yang Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chengyuan Li Dayiheng Liu Fei Huang Haoran Wei et al. 2024. Qwen2.5 Technical Report. arXiv preprint arXiv:2412.15115 (2024)."},{"key":"e_1_3_2_1_111_1","volume-title":"Proceedings of the 29th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)","author":"Yang Chaoqi","year":"2023","unstructured":"Chaoqi Yang, Zhenbang Wu, Patrick Jiang, Zhen Lin, Junyi Gao, Benjamin Danek, and Jimeng Sun. 2023. PyHealth: A Deep Learning Toolkit for Healthcare Predictive Modeling. In Proceedings of the 29th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD) 2023. https:\/\/github.com\/sunlabuiuc\/PyHealth"},{"key":"e_1_3_2_1_112_1","volume-title":"Gmai-mmbench: A comprehensive multimodal evaluation benchmark towards general medical ai. Advances in Neural Information Processing Systems, V37","author":"Ye Jin","year":"2024","unstructured":"Jin Ye, Guoan Wang, Yanjun Li, Zhongying Deng, Wei Li, Tianbin Li, Haodong Duan, Ziyan Huang, Yanzhou Su, Benyou Wang, et al., 2024. Gmai-mmbench: A comprehensive multimodal evaluation benchmark towards general medical ai. Advances in Neural Information Processing Systems, V37 (2024), 94327-94427."},{"key":"e_1_3_2_1_113_1","volume-title":"Yi: Open foundation models by 01. ai. arXiv preprint arXiv:2403.04652","author":"Young Alex","year":"2024","unstructured":"Alex Young, Bei Chen, Chao Li, Chengen Huang, Ge Zhang, Guanwei Zhang, et al., 2024. Yi: Open foundation models by 01. ai. arXiv preprint arXiv:2403.04652 (2024)."},{"key":"e_1_3_2_1_114_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"e_1_3_2_1_115_1","volume-title":"Ultramedical: Building specialized generalists in biomedicine. Advances in Neural Information Processing Systems, V37","author":"Zhang Kaiyan","year":"2024","unstructured":"Kaiyan Zhang, Sihang Zeng, Ermo Hua, Ning Ding, Zhang-Ren Chen, Zhiyuan Ma, Haoxin Li, Ganqu Cui, Biqing Qi, Xuekai Zhu, et al., 2024b. Ultramedical: Building specialized generalists in biomedicine. Advances in Neural Information Processing Systems, V37 (2024), 26045-26081."},{"key":"e_1_3_2_1_116_1","doi-asserted-by":"crossref","unstructured":"Ming Zhang Yujiong Shen Zelin Li Huayu Sha Binze Hu Yuhui Wang Chenhao Huang Shichun Liu Jingqi Tong Changhao Jiang et al. 2025b. LLMEval-Med: A Real-world Clinical Benchmark for Medical LLMs with Physician Validation. arXiv preprint arXiv:2506.04078 (2025).","DOI":"10.18653\/v1\/2025.findings-emnlp.263"},{"key":"e_1_3_2_1_117_1","volume-title":"Pmc-vqa: Visual instruction tuning for medical visual question answering. arXiv preprint arXiv:2305.10415","author":"Zhang Xiaoman","year":"2023","unstructured":"Xiaoman Zhang, Chaoyi Wu, Ziheng Zhao, Weixiong Lin, Ya Zhang, Yanfeng Wang, and Weidi Xie. 2023. Pmc-vqa: Visual instruction tuning for medical visual question answering. arXiv preprint arXiv:2305.10415 (2023)."},{"key":"e_1_3_2_1_118_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671594"},{"key":"e_1_3_2_1_119_1","volume-title":"V329","author":"Zhang Ziyang","year":"2025","unstructured":"Ziyang Zhang, WANG Lily, MENG Weimin, LIU Chang, SHAO Hui, V SUN Yan, GUO Jingchuan, BIAN Jiang, YIN Rui, and YANG Carl. 2025a. Type 2 Diabetes Subtyping via Phenotype and Genotype Co-Learning. Studies in health technology and informatics, V329 (2025), 1064."},{"key":"e_1_3_2_1_120_1","doi-asserted-by":"crossref","unstructured":"Shuang Zhou Wenya Xie Jiaxi Li Zaifu Zhan Meijia Song Han Yang Cheyenna Espinoza Lindsay Welton Xinnie Mai Yanwei Jin et al. 2025b. Automating expert-level medical reasoning evaluation of large language models. npj Digital Medicine (2025).","DOI":"10.1038\/s41746-025-02208-7"},{"key":"e_1_3_2_1_121_1","volume-title":"Multifaceteval: Multifaceted evaluation to probe llms in mastering medical knowledge. arXiv preprint arXiv:2406.02919","author":"Zhou Yuxuan","year":"2024","unstructured":"Yuxuan Zhou, Xien Liu, Chen Ning, and Ji Wu. 2024. Multifaceteval: Multifaceted evaluation to probe llms in mastering medical knowledge. arXiv preprint arXiv:2406.02919 (2024)."},{"key":"e_1_3_2_1_122_1","unstructured":"Z. Zhou et al. 2025a. Large language models for disease diagnosis: a scoping review. NPJ Digital Medicine (2025)."},{"key":"e_1_3_2_1_123_1","volume-title":"DiagnosisArena: Benchmarking Diagnostic Reasoning for Large Language Models. arXiv preprint arXiv:2505.14107","author":"Zhu Yakun","year":"2025","unstructured":"Yakun Zhu, Zhongzhen Huang, Linjie Mu, Yutong Huang, Wei Nie, Jiaji Liu, Shaoting Zhang, Pengfei Liu, and Xiaofan Zhang. 2025. DiagnosisArena: Benchmarking Diagnostic Reasoning for Large Language Models. arXiv preprint arXiv:2505.14107 (2025)."},{"key":"e_1_3_2_1_124_1","volume-title":"Medxpertqa: Benchmarking expert-level medical reasoning and understanding. arXiv preprint arXiv:2501.18362","author":"Zuo Yuxin","year":"2025","unstructured":"Yuxin Zuo, Shang Qu, Yifei Li, Zhangren Chen, Xuekai Zhu, Ermo Hua, Kaiyan Zhang, Ning Ding, and Bowen Zhou. 2025. Medxpertqa: Benchmarking expert-level medical reasoning and understanding. arXiv preprint arXiv:2501.18362 (2025)."}],"event":{"name":"KDD '26: The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Jeju Island Republic of Korea","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:21:17Z","timestamp":1786065677000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3817571"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":124,"alternative-id":["10.1145\/3770855.3817571","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3817571","relation":{},"subject":[],"published":{"date-parts":[[2026,8,8]]},"assertion":[{"value":"2026-08-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}