{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:40:41Z","timestamp":1786120841225,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":76,"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\/4.0\/legalcode"}],"funder":[{"name":"NSF (National Science Foundation)","award":["IIS-2506643"],"award-info":[{"award-number":["IIS-2506643"]}]},{"name":"NSF (National Science Foundation)","award":["POSE-234615"],"award-info":[{"award-number":["POSE-234615"]}]},{"name":"NAIRR Pilot","award":["260038"],"award-info":[{"award-number":["260038"]}]},{"name":"Cisco Research","award":["n\/a"],"award-info":[{"award-number":["n\/a"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770855.3818831","type":"proceedings-article","created":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T17:15:37Z","timestamp":1786036537000},"page":"10567-10577","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["ClinicalBench: Can LLMs Beat Traditional ML Models in Clinical Prediction?"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0937-1046","authenticated-orcid":false,"given":"Canyu","family":"Chen","sequence":"first","affiliation":[{"name":"Department of Computer Science, Northwestern University, Evanston, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8223-4597","authenticated-orcid":false,"given":"Jian","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Texas at Austin, Austin, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7999-7410","authenticated-orcid":false,"given":"Shan","family":"Chen","sequence":"additional","affiliation":[{"name":"Mass General Brigham and Boston Children's Hospital, Harvard Medical School, Boston, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3738-7998","authenticated-orcid":false,"given":"Che","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Imperial College London, London, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2790-0290","authenticated-orcid":false,"given":"Zhongwei","family":"Wan","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Ohio State University, Columbus, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5739-1637","authenticated-orcid":false,"given":"Shuang","family":"Zhou","sequence":"additional","affiliation":[{"name":"Massachusetts General Hospital, Harvard Medical School, Boston, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0195-7456","authenticated-orcid":false,"given":"Yuan","family":"Luo","sequence":"additional","affiliation":[{"name":"Department of Preventive Medicine, Feinberg School of Medicine, Northwestern University, Chicago, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8258-3585","authenticated-orcid":false,"given":"Rui","family":"Zhang","sequence":"additional","affiliation":[{"name":"Division of Computational Health Sciences, Department of Surgery, University of Minnesota, Minneapolis, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0345-2232","authenticated-orcid":false,"given":"Danielle","family":"Bitterman","sequence":"additional","affiliation":[{"name":"Mass General Brigham and Boston Children's Hospital, Harvard Medical School, Boston, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9459-9461","authenticated-orcid":false,"given":"Fei","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Population Health Sciences, Weill Cornell Medicine, Cornell University, New York, 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":"Department of Computer Science, Emory University, Atlanta, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2024.102938"},{"key":"e_1_3_2_1_2_1","volume-title":"V164","author":"Artetxe Arkaitz","year":"2018","unstructured":"Arkaitz Artetxe, Andoni Beristain, and Manuel Grana. 2018. Predictive models for hospital readmission risk: A systematic review of methods. Computer methods and programs in biomedicine, V164 (2018), 49-64."},{"key":"e_1_3_2_1_3_1","volume-title":"Vabs\/2401.02524","author":"Bauer Andr\u00e9","year":"2024","unstructured":"Andr\u00e9 Bauer, Simon Trapp, Michael Stenger, Robert Leppich, Samuel Kounev, Mark Leznik, Kyle Chard, and Ian Foster. 2024. Comprehensive exploration of synthetic data generation: A survey. ArXiv preprint, Vabs\/2401.02524 (2024). https:\/\/arxiv.org\/abs\/2401.02524"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29723"},{"key":"e_1_3_2_1_5_1","volume-title":"Vabs\/2402.18060","author":"Chen Hanjie","year":"2024","unstructured":"Hanjie Chen, Zhouxiang Fang, Yash Singla, and Mark Dredze. 2024a. Benchmarking Large Language Models on Answering and Explaining Challenging Medical Questions. ArXiv preprint, Vabs\/2402.18060 (2024). https:\/\/arxiv.org\/abs\/2402.18060"},{"key":"e_1_3_2_1_6_1","unstructured":"Jiangjie Chen Xintao Wang Rui Xu Siyu Yuan Yikai Zhang Wei Shi Jian Xie Shuang Li Ruihan Yang Tinghui Zhu et al. 2024c. From persona to personalization: A survey on role-playing language agents. ArXiv preprint Vabs\/2404.18231 (2024). https:\/\/arxiv.org\/abs\/2404.18231"},{"key":"e_1_3_2_1_7_1","volume-title":"Xueqing Peng, Kalpana Raja, Rui Zhang, Zhiyong Lu, and Hua Xu.","author":"Chen Qingyu","year":"2023","unstructured":"Qingyu Chen, Jingcheng Du, Yan Hu, Vipina Kuttichi Keloth, Xueqing Peng, Kalpana Raja, Rui Zhang, Zhiyong Lu, and Hua Xu. 2023b. Large language models in biomedical natural language processing: benchmarks, baselines, and recommendations. ArXiv preprint, Vabs\/2305.16326 (2023). https:\/\/arxiv.org\/abs\/2305.16326"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671576"},{"key":"e_1_3_2_1_9_1","volume-title":"Angelika Romanou, Antoine Bonnet","author":"Chen Zeming","year":"2023","unstructured":"Zeming Chen, Alejandro Hern\u00e1ndez Cano, Angelika Romanou, Antoine Bonnet, Kyle Matoba, Francesco Salvi, Matteo Pagliardini, Simin Fan, Andreas K\u00f6pf, Amirkeivan Mohtashami, et al., 2023a. Meditron-70b: Scaling medical pretraining for large language models. ArXiv preprint, Vabs\/2311.16079 (2023). https:\/\/arxiv.org\/abs\/2311.16079"},{"key":"e_1_3_2_1_10_1","volume-title":"Vabs\/2408.06142","author":"Christophe Cl\u00e9ment","year":"2024","unstructured":"Cl\u00e9ment Christophe, Praveen K Kanithi, Tathagata Raha, Shadab Khan, and Marco AF Pimentel. 2024. Med42-v2: A suite of clinical llms. ArXiv preprint, Vabs\/2408.06142 (2024). https:\/\/arxiv.org\/abs\/2408.06142"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611978032.41"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599534"},{"key":"e_1_3_2_1_13_1","volume-title":"Vabs\/2301.00234","author":"Dong Qingxiu","year":"2023","unstructured":"Qingxiu Dong, Lei Li, Damai Dai, Ce Zheng, Zhiyong Wu, Baobao Chang, Xu Sun, Jingjing Xu, and Zhifang Sui. 2023. A survey on in-context learning. ArXiv preprint, Vabs\/2301.00234 (2023). https:\/\/arxiv.org\/abs\/2301.00234"},{"key":"e_1_3_2_1_14_1","unstructured":"Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Amy Yang Angela Fan et al. 2024. The llama 3 herd of models. ArXiv preprint Vabs\/2407.21783 (2024). https:\/\/arxiv.org\/abs\/2407.21783"},{"key":"e_1_3_2_1_15_1","volume-title":"Khaldoun Zine El Abidine, and Christina Mack","author":"Feng Hui","year":"2024","unstructured":"Hui Feng, Francesco Ronzano, Jude LaFleur, Matthew Garber, Rodrigo de Oliveira, Kathryn Rough, Katharine Roth, Jay Nanavati, Khaldoun Zine El Abidine, and Christina Mack. 2024. Evaluation of Large Language Model Performance on the Biomedical Language Understanding and Reasoning Benchmark: Comparative Study. medRxiv (2024), 2024-05."},{"key":"e_1_3_2_1_16_1","volume-title":"Hugo Aerts, Thomas Hartvigsen, and Danielle Bitterman.","author":"Gallifant Jack","year":"2024","unstructured":"Jack Gallifant, Shan Chen, Pedro Moreira, Nikolaj Munch, Mingye Gao, Jackson Pond, Leo Anthony Celi, Hugo Aerts, Thomas Hartvigsen, and Danielle Bitterman. 2024. Language Models are Surprisingly Fragile to Drug Names in Biomedical Benchmarks. ArXiv preprint, Vabs\/2406.12066 (2024). https:\/\/arxiv.org\/abs\/2406.12066"},{"key":"e_1_3_2_1_17_1","volume-title":"David Chartash, et al.","author":"Gilson Aidan","year":"2023","unstructured":"Aidan Gilson, Conrad W Safranek, Thomas Huang, Vimig Socrates, Ling Chi, Richard Andrew Taylor, David Chartash, et al., 2023. How does ChatGPT perform on the United States Medical Licensing Examination (USMLE)? The implications of large language models for medical education and knowledge assessment. JMIR medical education, V9, 1 (2023), e45312."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"Paul Hager Friederike Jungmann Robbie Holland Kunal Bhagat Inga Hubrecht Manuel Knauer Jakob Vielhauer Marcus Makowski Rickmer Braren Georgios Kaissis et al. 2024. Evaluation and mitigation of the limitations of large language models in clinical decision-making. Nature medicine V30 9 (2024) 2613-2622.","DOI":"10.1038\/s41591-024-03097-1"},{"key":"e_1_3_2_1_19_1","volume-title":"Vabs\/2403.03744","author":"Han Tessa","year":"2024","unstructured":"Tessa Han, Aounon Kumar, Chirag Agarwal, and Himabindu Lakkaraju. 2024. Towards safe and aligned large language models for medicine. ArXiv preprint, Vabs\/2403.03744 (2024). https:\/\/arxiv.org\/abs\/2403.03744"},{"key":"e_1_3_2_1_20_1","unstructured":"Joshua Harris Timothy Laurence Leo Loman Fan Grayson Toby Nonnenmacher Harry Long Loes WalsGriffith Amy Douglas Holly Fountain Stelios Georgiou et al. 2024. Evaluating Large Language Models for Public Health Classification and Extraction Tasks. ArXiv preprint Vabs\/2405.14766 (2024). https:\/\/arxiv.org\/abs\/2405.14766"},{"key":"e_1_3_2_1_21_1","volume-title":"Measuring Massive Multitask Language Understanding. In 9th International Conference on Learning Representations, ICLR 2021","author":"Hendrycks Dan","year":"2021","unstructured":"Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt. 2021. Measuring Massive Multitask Language Understanding. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021. OpenReview.net. https:\/\/openreview.net\/forum?id=d7KBjmI3GmQ"},{"key":"e_1_3_2_1_22_1","volume-title":"LoRA: Low-Rank Adaptation of Large Language Models. In The Tenth International Conference on Learning Representations, ICLR 2022","author":"Hu Edward J.","year":"2022","unstructured":"Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. LoRA: Low-Rank Adaptation of Large Language Models. In The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022. OpenReview.net. https:\/\/openreview.net\/forum?id=nZeVKeeFYf9"},{"key":"e_1_3_2_1_23_1","volume-title":"Chun Peng, and Jimmy Xiangji Huang.","author":"Jahan Israt","year":"2024","unstructured":"Israt Jahan, Md Tahmid Rahman Laskar, Chun Peng, and Jimmy Xiangji Huang. 2024. A comprehensive evaluation of large language models on benchmark biomedical text processing tasks. Computers in biology and medicine, V171 (2024), 108189."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1093\/ehjacc\/zuaa021"},{"key":"e_1_3_2_1_25_1","volume-title":"GraphCare: Enhancing Healthcare Predictions with Personalized Knowledge Graphs. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=tVTN7Zs0ml","author":"Jiang Pengcheng","year":"2024","unstructured":"Pengcheng Jiang, Cao Xiao, Adam Richard Cross, and Jimeng Sun. 2024. GraphCare: Enhancing Healthcare Predictions with Personalized Knowledge Graphs. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=tVTN7Zs0ml"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.3390\/app11146421"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","unstructured":"Qiao Jin Fangyuan Chen Yiliang Zhou Ziyang Xu Justin M Cheung Robert Chen Ronald M Summers Justin F Rousseau Peiyun Ni Marc J Landsman et al. 2024. Hidden flaws behind expert-level accuracy of gpt-4 vision in medicine. ArXiv preprint Vabs\/2401.08396 (2024). https:\/\/arxiv.org\/abs\/2401.08396","DOI":"10.1038\/s41746-024-01185-7"},{"key":"e_1_3_2_1_28_1","volume-title":"Leo Anthony Celi, and Roger Mark","author":"Johnson Alistair","year":"2020","unstructured":"Alistair Johnson, Lucas Bulgarelli, Tom Pollard, Steven Horng, Leo Anthony Celi, and Roger Mark. 2020. Mimic-iv. PhysioNet. Available online at: https:\/\/physionet.org\/content\/mimiciv\/1.0\/(accessed August 23, 2021) (2020), 49-55."},{"key":"e_1_3_2_1_29_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_30_1","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2023.8288"},{"key":"e_1_3_2_1_31_1","volume-title":"Vabs\/2303.18027","author":"Kasai Jungo","year":"2023","unstructured":"Jungo Kasai, Yuhei Kasai, Keisuke Sakaguchi, Yutaro Yamada, and Dragomir Radev. 2023. Evaluating gpt-4 and chatgpt on japanese medical licensing examinations. ArXiv preprint, Vabs\/2303.18027 (2023). https:\/\/arxiv.org\/abs\/2303.18027"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"crossref","unstructured":"Evangelia Katsoulakis Qi Wang Huanmei Wu Leili Shahriyari Richard Fletcher Jinwei Liu Luke Achenie Hongfang Liu Pamela Jackson Ying Xiao et al. 2024. Digital twins for health: a scoping review. NPJ Digital Medicine V7 1 (2024) 77.","DOI":"10.1038\/s41746-024-01073-0"},{"key":"e_1_3_2_1_33_1","volume-title":"Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa.","author":"Kojima Takeshi","year":"2022","unstructured":"Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa. 2022. Large language models are zero-shot reasoners. Advances in neural information processing systems, V35 (2022), 22199-22213."},{"key":"e_1_3_2_1_34_1","volume-title":"Vabs\/2310.07225","author":"Korgul Karolina","year":"2023","unstructured":"Karolina Korgul, Andrew M Bean, Felix Krones, Robert McCraith, and Adam Mahdi. 2023. Exploring the landscape of large language models in medical question answering: Observations and open questions. ArXiv preprint, Vabs\/2310.07225 (2023). https:\/\/arxiv.org\/abs\/2310.07225"},{"key":"e_1_3_2_1_35_1","volume-title":"Rae Woong Park, and Edward Choi","author":"Kweon Sunjun","year":"2024","unstructured":"Sunjun Kweon, Byungjin Choi, Minkyu Kim, Rae Woong Park, and Edward Choi. 2024. KorMedMCQA: Multi-Choice Question Answering Benchmark for Korean Healthcare Professional Licensing Examinations. ArXiv preprint, Vabs\/2403.01469 (2024). https:\/\/arxiv.org\/abs\/2403.01469"},{"key":"e_1_3_2_1_36_1","unstructured":"Junling Liu Peilin Zhou Yining Hua Dading Chong Zhongyu Tian Andrew Liu Helin Wang Chenyu You Zhenhua Guo Lei Zhu et al. 2024d. Benchmarking large language models on cmexam-a comprehensive chinese medical exam dataset. Advances in Neural Information Processing Systems V36 (2024)."},{"key":"e_1_3_2_1_37_1","unstructured":"Lei Liu Xiaoyan Yang Junchi Lei Xiaoyang Liu Yue Shen Zhiqiang Zhang Peng Wei Jinjie Gu Zhixuan Chu Zhan Qin et al. 2024c. A Survey on Medical Large Language Models: Technology Application Trustworthiness and Future Directions. ArXiv preprint Vabs\/2406.03712 (2024). https:\/\/arxiv.org\/abs\/2406.03712"},{"key":"e_1_3_2_1_38_1","unstructured":"Mianxin Liu Jinru Ding Jie Xu Weiguo Hu Xiaoyang Li Lifeng Zhu Zhian Bai Xiaoming Shi Benyou Wang Haitao Song et al. 2024a. MedBench: A Comprehensive Standardized and Reliable Benchmarking System for Evaluating Chinese Medical Large Language Models. ArXiv preprint Vabs\/2407.10990 (2024). https:\/\/arxiv.org\/abs\/2407.10990"},{"key":"e_1_3_2_1_39_1","volume-title":"Best Practices and Lessons Learned on Synthetic Data. In First Conference on Language Modeling. https:\/\/openreview.net\/forum?id=OJaWBhh61C","author":"Liu Ruibo","unstructured":"Ruibo Liu, Jerry Wei, Fangyu Liu, Chenglei Si, Yanzhe Zhang, Jinmeng Rao, Steven Zheng, Daiyi Peng, Diyi Yang, Denny Zhou, and Andrew M. Dai. 2024b. Best Practices and Lessons Learned on Synthetic Data. In First Conference on Language Modeling. https:\/\/openreview.net\/forum?id=OJaWBhh61C"},{"key":"e_1_3_2_1_40_1","volume-title":"Large Language Model Instruction Following: A Survey of Progresses and Challenges. Computational Linguistics","author":"Lou Renze","year":"2024","unstructured":"Renze Lou, Kai Zhang, and Wenpeng Yin. 2024. Large Language Model Instruction Following: A Survey of Progresses and Challenges. Computational Linguistics (2024), 1-10."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2024.102904"},{"key":"e_1_3_2_1_42_1","unstructured":"Daniel McDuff Mike Schaekermann Tao Tu Anil Palepu Amy Wang Jake Garrison Karan Singhal Yash Sharma Shekoofeh Azizi Kavita Kulkarni et al. 2023. Towards accurate differential diagnosis with large language models. ArXiv preprint Vabs\/2312.00164 (2023). https:\/\/arxiv.org\/abs\/2312.00164"},{"key":"e_1_3_2_1_43_1","volume-title":"Bastian Dewitz, Roman Bibo","author":"Moazemi Sobhan","year":"2023","unstructured":"Sobhan Moazemi, Sahar Vahdati, Jason Li, Sebastian Kalkhoff, Luis JV Castano, Bastian Dewitz, Roman Bibo, Parisa Sabouniaghdam, Mohammad S Tootooni, Ralph A Bundschuh, et al., 2023. Artificial intelligence for clinical decision support for monitoring patients in cardiovascular ICUs: a systematic review. Frontiers in Medicine, V10 (2023), 1109411."},{"key":"e_1_3_2_1_44_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_45_1","volume-title":"Vabs\/2308.03188","author":"Pan Liangming","year":"2023","unstructured":"Liangming Pan, Michael Saxon, Wenda Xu, Deepak Nathani, Xinyi Wang, and William Yang Wang. 2023. Automatically correcting large language models: Surveying the landscape of diverse self-correction strategies. ArXiv preprint, Vabs\/2308.03188 (2023). https:\/\/arxiv.org\/abs\/2308.03188"},{"key":"e_1_3_2_1_46_1","volume-title":"V83","author":"Purushotham Sanjay","year":"2018","unstructured":"Sanjay Purushotham, Chuizheng Meng, Zhengping Che, and Yan Liu. 2018. Benchmarking deep learning models on large healthcare datasets. Journal of biomedical informatics, V83 (2018), 112-134."},{"key":"e_1_3_2_1_47_1","volume-title":"Vabs\/2404.04575","author":"Qiu Zi-Hao","year":"2024","unstructured":"Zi-Hao Qiu, Siqi Guo, Mao Xu, Tuo Zhao, Lijun Zhang, and Tianbao Yang. 2024. To Cool or not to Cool? Temperature Network Meets Large Foundation Models via DRO. ArXiv preprint, Vabs\/2404.04575 (2024). https:\/\/arxiv.org\/abs\/2404.04575"},{"key":"e_1_3_2_1_48_1","volume-title":"V380, 14","author":"Rajkomar Alvin","year":"2019","unstructured":"Alvin Rajkomar, Jeffrey Dean, and Isaac Kohane. 2019. Machine learning in medicine. New England Journal of Medicine, V380, 14 (2019), 1347-1358."},{"key":"e_1_3_2_1_49_1","volume-title":"Vabs\/2402.05201","author":"Renze Matthew","year":"2024","unstructured":"Matthew Renze and Erhan Guven. 2024. The effect of sampling temperature on problem solving in large language models. ArXiv preprint, Vabs\/2402.05201 (2024). https:\/\/arxiv.org\/abs\/2402.05201"},{"key":"e_1_3_2_1_50_1","volume-title":"V13, 1","author":"Roso\u0142 Maciej","year":"2023","unstructured":"Maciej Roso\u0142, Jakub S G\u0105sior, Jonasz \u0141aba, Kacper Korzeniewski, and Marcel M\u0142y\u0144czak. 2023. Evaluation of the performance of GPT-3.5 and GPT-4 on the Polish Medical Final Examination. Scientific Reports, V13, 1 (2023), 20512."},{"key":"e_1_3_2_1_51_1","volume-title":"Sriparna Saha, Vinija Jain, Samrat Mondal, and Aman Chadha.","author":"Sahoo Pranab","year":"2024","unstructured":"Pranab Sahoo, Ayush Kumar Singh, Sriparna Saha, Vinija Jain, Samrat Mondal, and Aman Chadha. 2024. A systematic survey of prompt engineering in large language models: Techniques and applications. ArXiv preprint, Vabs\/2402.07927 (2024). https:\/\/arxiv.org\/abs\/2402.07927"},{"key":"e_1_3_2_1_52_1","unstructured":"Sander Schulhoff Michael Ilie Nishant Balepur Konstantine Kahadze Amanda Liu Chenglei Si Yinheng Li Aayush Gupta HyoJung Han Sevien Schulhoff et al. 2024. The Prompt Report: A Systematic Survey of Prompting Techniques. ArXiv preprint Vabs\/2406.06608 (2024). https:\/\/arxiv.org\/abs\/2406.06608"},{"key":"e_1_3_2_1_53_1","volume-title":"Vabs\/2405.07348","author":"Shoham Ofir Ben","year":"2024","unstructured":"Ofir Ben Shoham and Nadav Rappoport. 2024. MedConceptsQA-Open Source Medical Concepts QA Benchmark. ArXiv preprint, Vabs\/2405.07348 (2024). https:\/\/arxiv.org\/abs\/2405.07348"},{"key":"e_1_3_2_1_54_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., 2023a. Large language models encode clinical knowledge. Nature, V620, 7972 (2023), 172-180."},{"key":"e_1_3_2_1_55_1","unstructured":"Karan Singhal Tao Tu Juraj Gottweis Rory Sayres Ellery Wulczyn Le Hou Kevin Clark Stephen Pfohl Heather Cole-Lewis Darlene Neal et al. 2023b. Towards expert-level medical question answering with large language models. ArXiv preprint Vabs\/2305.09617 (2023). https:\/\/arxiv.org\/abs\/2305.09617"},{"key":"e_1_3_2_1_56_1","volume-title":"V1, 4","author":"Stone Kieran","year":"2022","unstructured":"Kieran Stone, Reyer Zwiggelaar, Phil Jones, and Neil Mac Parthal\u00e1in. 2022. A systematic review of the prediction of hospital length of stay: Towards a unified framework. PLOS Digital Health, V1, 4 (2022), e0000017."},{"key":"e_1_3_2_1_57_1","volume-title":"V9","author":"Sun Tianze","year":"2023","unstructured":"Tianze Sun, Xiwang He, and Zhonghai Li. 2023. Digital twin in healthcare: Recent updates and challenges. Digital Health, V9 (2023), 20552076221149651."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"crossref","unstructured":"Zhen Tan Alimohammad Beigi Song Wang Ruocheng Guo Amrita Bhattacharjee Bohan Jiang Mansooreh Karami Jundong Li Lu Cheng and Huan Liu. 2024. Large Language Models for Data Annotation: A Survey. arXiv:2402.13446 [cs.CL]","DOI":"10.18653\/v1\/2024.emnlp-main.54"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocaa139"},{"key":"e_1_3_2_1_60_1","volume-title":"Yet Another ICU Benchmark: A Flexible Multi-Center Framework for Clinical ML. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=ox2ATRM90I","author":"van de Water Robin","year":"2024","unstructured":"Robin van de Water, Hendrik Nils Aurel Schmidt, Paul Elbers, Patrick Thoral, Bert Arnrich, and Patrick Rockenschaub. 2024. Yet Another ICU Benchmark: A Flexible Multi-Center Framework for Clinical ML. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=ox2ATRM90I"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.860"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3611651","article-title":"Pre-trained language models in biomedical domain: A systematic survey","volume":"56","author":"Wang Benyou","year":"2023","unstructured":"Benyou Wang, Qianqian Xie, Jiahuan Pei, Zhihong Chen, Prayag Tiwari, Zhao Li, and Jie Fu. 2023b. Pre-trained language models in biomedical domain: A systematic survey. Comput. Surveys, V56, 3 (2023), 1-52.","journal-title":"Comput. Surveys"},{"key":"e_1_3_2_1_63_1","unstructured":"Chong Wang Mengyao Li Junjun He Zhongruo Wang Erfan Darzi Zan Chen Jin Ye Tianbin Li Yanzhou Su Jing Ke et al. 2024a. A Survey for Large Language Models in Biomedicine. ArXiv preprint Vabs\/2409.00133 (2024). https:\/\/arxiv.org\/abs\/2409.00133"},{"key":"e_1_3_2_1_64_1","volume-title":"Vabs\/2408.08422","author":"Wang Guanchu","year":"2024","unstructured":"Guanchu Wang, Junhao Ran, Ruixiang Tang, Chia-Yuan Chang, Yu-Neng Chuang, Zirui Liu, Vladimir Braverman, Zhandong Liu, and Xia Hu. 2024c. Assessing and Enhancing Large Language Models in Rare Disease Question-answering. ArXiv preprint, Vabs\/2408.08422 (2024). https:\/\/arxiv.org\/abs\/2408.08422"},{"key":"e_1_3_2_1_65_1","unstructured":"Jiaqi Wang Junyu Luo Muchao Ye Xiaochen Wang Yuan Zhong Aofei Chang Guanjie Huang Ziyi Yin Cao Xiao Jimeng Sun et al. 2024b. Recent Advances in Predictive Modeling with Electronic Health Records. ArXiv preprint Vabs\/2402.01077 (2024). https:\/\/arxiv.org\/abs\/2402.01077"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/3368555.3384469"},{"key":"e_1_3_2_1_67_1","volume-title":"Dingjie Song, Zhiyi Zhang, Zhihong Chen, Qingying Xiao, Feng Jiang, Jianquan Li, Xiang Wan, Benyou Wang, et al.","author":"Wang Xidong","year":"2023","unstructured":"Xidong Wang, Guiming Hardy Chen, Dingjie Song, Zhiyi Zhang, Zhihong Chen, Qingying Xiao, Feng Jiang, Jianquan Li, Xiang Wan, Benyou Wang, et al., 2023a. Cmb: A comprehensive medical benchmark in chinese. ArXiv preprint, Vabs\/2308.08833 (2023). https:\/\/arxiv.org\/abs\/2308.08833"},{"key":"e_1_3_2_1_68_1","volume-title":"A Perspective for Adapting Generalist AI to Specialized Medical AI Applications and Their Challenges. arXiv preprint arXiv: 2411.00024","author":"Wang Zifeng","year":"2024","unstructured":"Zifeng Wang, Hanyin Wang, Benjamin Danek, Ying Li, Christina Mack, Hoifung Poon, Yajun Wang, Pranav Rajpurkar, and Jimeng Sun. 2024d. A Perspective for Adapting Generalist AI to Specialized Medical AI Applications and Their Challenges. arXiv preprint arXiv: 2411.00024 (2024)."},{"key":"e_1_3_2_1_69_1","volume-title":"AMIA Summits on Translational Science Proceedings, V2023","author":"Xu Ran","year":"2023","unstructured":"Ran Xu, Mohammed K Ali, Joyce C Ho, and Carl Yang. 2023. Hypergraph transformers for ehr-based clinical predictions. AMIA Summits on Translational Science Proceedings, V2023 (2023), 582."},{"key":"e_1_3_2_1_70_1","unstructured":"An Yang Baosong Yang Binyuan Hui Bo Zheng Bowen Yu Chang Zhou Chengpeng Li Chengyuan Li Dayiheng Liu Fei Huang et al. 2024. Qwen2 technical report. ArXiv preprint Vabs\/2407.10671 (2024). https:\/\/arxiv.org\/abs\/2407.10671"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599178"},{"key":"e_1_3_2_1_72_1","volume-title":"Yi: Open foundation models by 01. ai. ArXiv preprint, Vabs\/2403.04652","author":"Young Alex","year":"2024","unstructured":"Alex Young, Bei Chen, Chao Li, Chengen Huang, Ge Zhang, Guanwei Zhang, Heng Li, Jiangcheng Zhu, Jianqun Chen, Jing Chang, et al., 2024. Yi: Open foundation models by 01. ai. ArXiv preprint, Vabs\/2403.04652 (2024). https:\/\/arxiv.org\/abs\/2403.04652"},{"key":"e_1_3_2_1_73_1","unstructured":"Shengyu Zhang Linfeng Dong Xiaoya Li Sen Zhang Xiaofei Sun Shuhe Wang Jiwei Li Runyi Hu Tianwei Zhang Fei Wu et al. 2023. Instruction tuning for large language models: A survey. ArXiv preprint Vabs\/2308.10792 (2023). https:\/\/arxiv.org\/abs\/2308.10792"},{"key":"e_1_3_2_1_74_1","volume-title":"Agieval: A human-centric benchmark for evaluating foundation models. ArXiv preprint, Vabs\/2304.06364","author":"Zhong Wanjun","year":"2023","unstructured":"Wanjun Zhong, Ruixiang Cui, Yiduo Guo, Yaobo Liang, Shuai Lu, Yanlin Wang, Amin Saied, Weizhu Chen, and Nan Duan. 2023. Agieval: A human-centric benchmark for evaluating foundation models. ArXiv preprint, Vabs\/2304.06364 (2023). https:\/\/arxiv.org\/abs\/2304.06364"},{"key":"e_1_3_2_1_75_1","unstructured":"Hongjian Zhou Boyang Gu Xinyu Zou Yiru Li Sam S Chen Peilin Zhou Junling Liu Yining Hua Chengfeng Mao Xian Wu et al. 2023. A survey of large language models in medicine: Progress application and challenge. ArXiv preprint Vabs\/2311.05112 (2023). https:\/\/arxiv.org\/abs\/2311.05112"},{"key":"e_1_3_2_1_76_1","unstructured":"Shuang Zhou Zidu Xu Mian Zhang Chunpu Xu Yawen Guo Zaifu Zhan Sirui Ding Jiashuo Wang Kaishuai Xu Yi Fang et al. 2024. Large Language Models for Disease Diagnosis: A Scoping Review. ArXiv preprint Vabs\/2409.00097 (2024). https:\/\/arxiv.org\/abs\/2409.00097"}],"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":"2026-08-07T01:18:32Z","timestamp":1786065512000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3818831"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":76,"alternative-id":["10.1145\/3770855.3818831","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3818831","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"}}]}}