{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T15:59:40Z","timestamp":1785340780536,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T00:00:00Z","timestamp":1782777600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"ESF+ 2021\/2027 Regional Program of the Autonomous Region Friuli Venezia Giulia","award":["PPO 2023, Program No. 22\/23 \u2013 LINE A: PhD programmes"],"award-info":[{"award-number":["PPO 2023, Program No. 22\/23 \u2013 LINE A: PhD programmes"]}]},{"name":"Supporting the diagnosis of rare diseases (MR) through artificial intelligence","award":["F53C22001770002"],"award-info":[{"award-number":["F53C22001770002"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,30]]},"DOI":"10.1145\/3807503.3819373","type":"proceedings-article","created":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T02:55:27Z","timestamp":1785293727000},"page":"1-6","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Probing the Intrinsic Effectiveness of Large Language Models for Medical Classifications"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-5550-317X","authenticated-orcid":false,"given":"Riccardo","family":"Lunardi","sequence":"first","affiliation":[{"name":"University of Udine, Udine, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9191-3280","authenticated-orcid":false,"given":"Kevin","family":"Roitero","sequence":"additional","affiliation":[{"name":"University of Udine, Udine, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0144-3802","authenticated-orcid":false,"given":"Vincenzo","family":"Della Mea","sequence":"additional","affiliation":[{"name":"University of Udine, Udine, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,28]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"crossref","unstructured":"Swapna Abhyankar Dina Demner-Fushman Fiona\u00a0M Callaghan et\u00a0al. 2014. Combining structured and unstructured data to identify a cohort of ICU patients who received dialysis. Journal of the American Medical Informatics Association 21 5 (01 2014).","DOI":"10.1136\/amiajnl-2013-001915"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/RE63999.2025.00023"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"crossref","unstructured":"David Arps Younes Samih Laura Kallmeyer et\u00a0al. 2022. Probing for constituency structure in neural language models. arXiv:https:\/\/arXiv.org\/abs\/2204.06201 (2022).","DOI":"10.18653\/v1\/2022.findings-emnlp.502"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"crossref","unstructured":"M Ashburner C\u00a0A Ball J\u00a0A Blake et\u00a0al. 2000. Gene ontology: tool for the unification of biology. Nat. Genet. 25 1 (May 2000).","DOI":"10.1038\/75556"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"crossref","unstructured":"Yonatan Belinkov. 2022. Probing classifiers: Promises shortcomings and advances. Computational Linguistics 48 1 (2022).","DOI":"10.1162\/coli_a_00422"},{"key":"e_1_3_3_2_7_2","volume-title":"ICLR","author":"Berglund Lukas","year":"2024","unstructured":"Lukas Berglund, Meg Tong, Maximilian Kaufmann, et\u00a0al. 2024. The Reversal Curse: LLMs trained on \u201cA is B\u201d fail to learn \u201cB is A\u201d. In ICLR , Vol.\u00a02024."},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"crossref","unstructured":"Kathrin Blagec Georg Dorffner Milad Moradi et\u00a0al. 2022. A global analysis of metrics used for measuring performance in natural language processing. arXiv:https:\/\/arXiv.org\/abs\/2204.11574 (2022).","DOI":"10.18653\/v1\/2022.nlppower-1.6"},{"key":"e_1_3_3_2_9_2","volume-title":"Adv. NeurIPS","author":"Brown Tom","year":"2020","unstructured":"Tom Brown, Benjamin Mann, Nick Ryder, et\u00a0al. 2020. Language Models are Few-Shot Learners. In Adv. NeurIPS , Vol.\u00a033. Curran Associates, Inc."},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.59"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"crossref","unstructured":"Yunzhi Chen Huijuan Lu and Lanjuan Li. 2017. Automatic ICD-10 coding algorithm using an improved longest common subsequence based on semantic similarity. PLoS One 12 3 (March 2017).","DOI":"10.1371\/journal.pone.0173410"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2844"},{"key":"e_1_3_3_2_13_2","unstructured":"Aaron\u00a0Grattafiori et al.2024. The Llama 3 Herd of Models."},{"key":"e_1_3_3_2_14_2","unstructured":"Alexander H.\u00a0Liu et al. 2026. Ministral 3."},{"key":"e_1_3_3_2_15_2","unstructured":"Andrew\u00a0Sellergren et al.2025. MedGemma Technical Report."},{"key":"e_1_3_3_2_16_2","unstructured":"An\u00a0Yang et al.2025. Qwen3 Technical Report."},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"crossref","unstructured":"Georgios Feretzakis Evangelia Vagena et\u00a0al. 2025. GDPR and large language models: Technical and legal obstacles. Future Internet 17 4 (2025).","DOI":"10.3390\/fi17040151"},{"key":"e_1_3_3_2_18_2","unstructured":"WHO Collaborating\u00a0Centre for Drug Statistics\u00a0Methodology. 2001. ATC Index."},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"crossref","unstructured":"Gregor Jezernik Mario Gorenjak and Uro\u0161 Poto\u010dnik. 2022. Gene Ontology Analysis Highlights Biological Processes Influencing Non-Response to Anti-TNF Therapy in Rheumatoid Arthritis. Biomedicines 10 8 (2022).","DOI":"10.3390\/biomedicines10081808"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"crossref","unstructured":"Alistair E\u00a0W Johnson Tom\u00a0J Pollard Lu Shen et\u00a0al. 2016. MIMIC-III a freely accessible critical care database. Sci. Data 3 1 (May 2016).","DOI":"10.1038\/sdata.2016.35"},{"key":"e_1_3_3_2_21_2","unstructured":"Najoung Kim Roma Patel et\u00a0al. 2019. Probing what different NLP tasks teach machines about function word comprehension. arXiv:https:\/\/arXiv.org\/abs\/1904.11544 (2019)."},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1613"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"crossref","unstructured":"Fajri Koto Jey\u00a0Han Lau and Timothy Baldwin. 2021. Discourse probing of pretrained language models. arXiv:https:\/\/arXiv.org\/abs\/2104.05882 (2021).","DOI":"10.18653\/v1\/2021.naacl-main.301"},{"key":"e_1_3_3_2_24_2","unstructured":"Patrick Lewis Ethan Perez Aleksandra Piktus et\u00a0al. 2020. Retrieval-augmented generation for knowledge-intensive nlp tasks. Adv. NeurIPS 33 (2020)."},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"crossref","unstructured":"Xiaohong Liu Hao Liu Guoxing Yang et\u00a0al. 2025. A generalist medical language model for disease diagnosis assistance. Nature Medicine 31 3 (01 March 2025).","DOI":"10.1038\/s41591-024-03416-6"},{"key":"e_1_3_3_2_26_2","unstructured":"World\u00a0Health Organization. 2001. International classification of functioning disability and health : ICF."},{"key":"e_1_3_3_2_27_2","unstructured":"World\u00a0Health Organization. 2004. ICD-10 : international statistical classification of diseases and related health problems : tenth revision."},{"key":"e_1_3_3_2_28_2","volume-title":"Proc. COLING","author":"Papineni Kishore","year":"2002","unstructured":"Kishore Papineni, Salim Roukos, Todd Ward, et\u00a0al. 2002. Bleu: a Method for Automatic Evaluation of Machine Translation. In Proc. COLING. Association for Computational Linguistics, Philadelphia, Pennsylvania, USA."},{"key":"e_1_3_3_2_29_2","unstructured":"Qwen. 2025. Qwen2.5 Technical Report."},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"crossref","unstructured":"Karan Singhal Shekoofeh Azizi Tao Tu et\u00a0al. 2023. Large language models encode clinical knowledge. Nature 620 7972 (2023).","DOI":"10.1038\/s41586-023-06291-2"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"crossref","unstructured":"Ali Vaezi. 2025. Legal Challenges in the Deployment of Large Language Models: A Comparative Analysis under the GDPR and EU AI Act. SSRN5285174 (2025).","DOI":"10.2139\/ssrn.5285174"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"crossref","unstructured":"Eric Wallace Yizhong Wang Sujian Li et\u00a0al. 2019. Do NLP models know numbers? probing numeracy in embeddings. arXiv:https:\/\/arXiv.org\/abs\/1909.07940 (2019).","DOI":"10.18653\/v1\/D19-1534"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"crossref","unstructured":"Guangyu Wang Xiaohong Liu Zhen Ying et\u00a0al. 2023. Optimized glycemic control of type 2 diabetes with reinforcement learning: a proof-of-concept trial. Nature Medicine 29 10 (01 Oct. 2023).","DOI":"10.1038\/s41591-023-02552-9"},{"key":"e_1_3_3_2_34_2","unstructured":"Xuezhi Wang Jason Wei Dale Schuurmans et\u00a0al. 2022. Self-consistency improves chain of thought reasoning in language models. arXiv:https:\/\/arXiv.org\/abs\/2203.11171 (2022)."},{"key":"e_1_3_3_2_35_2","unstructured":"Valerie\u00a0JM Watzlaf Jennifer\u00a0Hornung Garvin Sohrab Moeini et\u00a0al. 2007. The effectiveness of ICD-10-CM in capturing public health diseases. Perspectives in health information management 4 1 (2007)."},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"crossref","unstructured":"Jason Wei Xuezhi Wang Dale Schuurmans et\u00a0al. 2022. Chain-of-thought prompting elicits reasoning in large language models. Adv. NeurIPS 35 (2022).","DOI":"10.52202\/068431-1800"},{"key":"e_1_3_3_2_37_2","unstructured":"72 World Health\u00a0Assembly. 2019. Eleventh revision of the International Classification of Diseases. (2019)."},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"crossref","unstructured":"An Yang Kai Liu Jing Liu et\u00a0al. 2018. Adaptations of ROUGE and BLEU to better evaluate machine reading comprehension task. arXiv:https:\/\/arXiv.org\/abs\/1806.03578 (2018).","DOI":"10.18653\/v1\/W18-2611"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"crossref","unstructured":"Haochen Zhao Guihua Duan Peng Ni et\u00a0al. 2023. RNPredATC: A deep residual learning-based model with applications to the prediction of drug-ATC code association. IEEE\/ACM Trans. Comput. Biol. Bioinform. 20 5 (Sept. 2023).","DOI":"10.1109\/TCBB.2021.3088256"}],"event":{"name":"BCB '26: 17th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","location":"Rende (CS) Italy","acronym":"BCB '26","sponsor":["SIGBio ACM Special Interest Group on Bioinformatics"]},"container-title":["Proceedings of the 17th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3807503.3819373","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T15:16:01Z","timestamp":1785338161000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3807503.3819373"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,30]]},"references-count":38,"alternative-id":["10.1145\/3807503.3819373","10.1145\/3807503"],"URL":"https:\/\/doi.org\/10.1145\/3807503.3819373","relation":{},"subject":[],"published":{"date-parts":[[2026,6,30]]},"assertion":[{"value":"2026-07-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}