{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,11]],"date-time":"2026-11-11T14:39:43Z","timestamp":1794407983649,"version":"4.9.0"},"reference-count":63,"publisher":"Elsevier BV","issue":"3","license":[{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2024,2,5]],"date-time":"2024-02-05T00:00:00Z","timestamp":1707091200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001732","name":"Danmarks Grundforskningsfond","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001732","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100009708","name":"Novo Nordisk Fonden","doi-asserted-by":"publisher","award":["NNF20OC0062606"],"award-info":[{"award-number":["NNF20OC0062606"]}],"id":[{"id":"10.13039\/501100009708","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["cell.com","elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Patterns"],"published-print":{"date-parts":[[2024,3]]},"DOI":"10.1016\/j.patter.2024.100943","type":"journal-article","created":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T10:28:50Z","timestamp":1709288930000},"page":"100943","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":258,"title":["Can large language models reason about medical questions?"],"prefix":"10.1016","volume":"5","author":[{"given":"Valentin","family":"Li\u00e9vin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christoffer Egeberg","family":"Hother","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andreas Geert","family":"Motzfeldt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1966-3205","authenticated-orcid":false,"given":"Ole","family":"Winther","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patter.2024.100943_bib1","article-title":"Distributed representations of words and phrases and their compositionality","volume":"26","author":"Mikolov","year":"2013","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patter.2024.100943_bib2","series-title":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)","first-page":"1532","article-title":"GloVe: Global vectors for word representation","author":"Pennington","year":"2014"},{"key":"10.1016\/j.patter.2024.100943_bib3","article-title":"Deep contextualized word representations","author":"Peters","year":"2018","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2024.100943_bib4","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patter.2024.100943_bib5","article-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","author":"Devlin","year":"2018","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2024.100943_bib6","series-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"10.1016\/j.patter.2024.100943_bib7","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patter.2024.100943_bib8","article-title":"Scaling Language Models: Methods, Analysis\u00a0& Insights from Training Gopher","author":"Rae","year":"2021","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2024.100943_bib9","first-page":"1","article-title":"Palm: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"J.\u00a0Mach. Learn. Res."},{"key":"10.1016\/j.patter.2024.100943_bib10","article-title":"LaMDA: Language Models for Dialog Applications","author":"Thoppilan","year":"2022","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2024.100943_bib11","article-title":"Training Compute-optimal Large Language Models","author":"Hoffmann","year":"2022","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2024.100943_bib12","article-title":"Using DeepSpeed and Megatron to Train Megatron-turing NLG 530B, A Large-scale Generative Language Model","author":"Smith","year":"2022","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2024.100943_bib13","article-title":"OPT: Open Pre-trained Transformer Language Models","author":"Zhang","year":"2022","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2024.100943_bib14","first-page":"9","article-title":"Jurassic-1: Technical details and evaluation","volume":"1","author":"Lieber","year":"2021","journal-title":"White Paper AI21 Labs"},{"key":"10.1016\/j.patter.2024.100943_bib15","first-page":"5232","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus","year":"2022","journal-title":"J.\u00a0Mach. Learn. Res."},{"key":"10.1016\/j.patter.2024.100943_bib16","first-page":"31809","article-title":"The BigScience ROOTS Corpus: A 1.6TB composite multilingual dataset","volume":"35","author":"Lauren\u00e7on","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patter.2024.100943_bib17","article-title":"Scaling Laws for Neural Language Models","author":"Kaplan","year":"2020","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2024.100943_bib18","article-title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","author":"Srivastava","year":"2022","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2024.100943_bib19","first-page":"1","article-title":"Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing","volume":"55","author":"Liu","year":"2023","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.patter.2024.100943_bib20","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patter.2024.100943_bib21","article-title":"Least-to-most Prompting Enables Complex Reasoning in Large Language Models","author":"Zhou","year":"2022","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2024.100943_bib22","article-title":"Compositional Semantic Parsing with Large Language Models","author":"Drozdov","year":"2022","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2024.100943_bib23","article-title":"Show Your Work: Scratchpads for Intermediate Computation with Language Models","author":"Nye","year":"2021","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2024.100943_bib24","article-title":"Challenging BIG-bench Tasks and Whether Chain-of-thought Can Solve Them","author":"Suzgun","year":"2022","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2024.100943_bib25","first-page":"22199","article-title":"Large language models are zero-shot reasoners","volume":"35","author":"Kojima","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patter.2024.100943_bib26","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patter.2024.100943_bib27","series-title":"Proceedings of the 2021 ACM conference on fairness, accountability, and transparency","first-page":"610","article-title":"On the dangers of stochastic parrots: Can language models be too big?","author":"Bender","year":"2021"},{"key":"10.1016\/j.patter.2024.100943_bib28","article-title":"Adversarial GLUE: A Multi-task Benchmark for Robustness Evaluation of Language Models","author":"Wang","year":"2021","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2024.100943_bib29","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1038\/s41746-021-00464-x","article-title":"Considering the possibilities and pitfalls of Generative Pre-trained Transformer 3 (GPT-3) in healthcare delivery","volume":"4","author":"Korngiebel","year":"2021","journal-title":"NPJ Digit. Med."},{"key":"10.1016\/j.patter.2024.100943_bib30","first-page":"10","article-title":"Operationalizing and Implementing Pretrained, Large Artificial Intelligence Linguistic Models in\u00a0the US Health Care System: Outlook of Generative Pretrained Transformer 3 (GPT-3) as a Service Model","author":"Sezgin","year":"2022","journal-title":"JMIR medical informatics"},{"key":"10.1016\/j.patter.2024.100943_bib31","article-title":"Measuring Massive Multitask Language Understanding","author":"Hendrycks","year":"2020","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2024.100943_bib32","doi-asserted-by":"crossref","first-page":"6421","DOI":"10.3390\/app11146421","article-title":"What disease does this patient have? a large-scale open domain question answering dataset from medical exams","volume":"11","author":"Jin","year":"2021","journal-title":"Appl. Sci."},{"key":"10.1016\/j.patter.2024.100943_bib33","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1038\/s41586-023-06291-2","article-title":"Large language models encode clinical knowledge","volume":"620","author":"Singhal","year":"2023","journal-title":"Nature"},{"key":"10.1016\/j.patter.2024.100943_bib34","article-title":"Towards Expert-level Medical Question Answering with Large Language Models","author":"Singhal","year":"2023","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2024.100943_bib35","article-title":"Capabilities of GPT-4 on Medical Challenge Problems","author":"Nori","year":"2023","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2024.100943_bib36","doi-asserted-by":"crossref","DOI":"10.2196\/45312","article-title":"How Does ChatGPT Perform on the United States Medical Licensing Examination? The Implications of Large Language Models for Medical Education and Knowledge Assessment","volume":"9","author":"Gilson","year":"2023","journal-title":"JMIR Med. Educ."},{"key":"10.1016\/j.patter.2024.100943_bib37","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pdig.0000198","article-title":"Performance of ChatGPT on USMLE: Potential for AI-assisted medical education using large language models","volume":"2","author":"Kung","year":"2023","journal-title":"PLOS Digit. Health"},{"key":"10.1016\/j.patter.2024.100943_bib38","article-title":"Llama 2: Open Foundation and Fine-tuned Chat Models","author":"Touvron","year":"2023","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2024.100943_bib39","article-title":"MEDITRON-70B: Scaling Medical Pretraining for Large Language Models","author":"Chen","year":"2023","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2024.100943_bib40","article-title":"Augmenting Black-box LLMs with Medical Textbooks for Clinical Question Answering","author":"Wang","year":"2023","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2024.100943_bib41","series-title":"International Conference on Machine Learning","first-page":"20950","article-title":"Variational open-domain question answering","author":"Li\u00e9vin","year":"2023"},{"key":"10.1016\/j.patter.2024.100943_bib42","article-title":"Self-consistency Improves Chain of Thought Reasoning in Language Models","author":"Wang","year":"2022","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2024.100943_bib43","article-title":"On the Advance of Making Language Models Better Reasoners","author":"Li","year":"2022","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2024.100943_bib44","first-page":"248","article-title":"Medmcqa: A large-scale multi-subject multi-choice dataset for medical domain question answering","volume":"174","author":"Pal","year":"2022","journal-title":"PMLR"},{"key":"10.1016\/j.patter.2024.100943_bib45","article-title":"PubMedQA: A Dataset for Biomedical Research Question Answering","author":"Jin","year":"2019","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2024.100943_bib46","article-title":"Scaling Instruction-finetuned Language Models","author":"Chung","year":"2022","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2024.100943_bib47","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","volume":"33","author":"Lewis","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patter.2024.100943_bib48","first-page":"2206","article-title":"Improving language models by retrieving from trillions of tokens","volume":"162","author":"Borgeaud","year":"2022","journal-title":"PMLR"},{"key":"10.1016\/j.patter.2024.100943_bib49","article-title":"Internet-augmented language models through few-shot prompting for open-domain question answering","author":"Lazaridou","year":"2022","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2024.100943_bib50","series-title":"Vlievin\/Medical-Reasoning: Official Release","author":"Li\u00e9vin","year":"2023"},{"key":"10.1016\/j.patter.2024.100943_bib51","first-page":"10","article-title":"ThoughtSource: A central hub for large language model reasoning data","author":"Ott","year":"2023","journal-title":"Sci. Data"},{"key":"10.1016\/j.patter.2024.100943_bib52","article-title":"Evaluating Large Language Models Trained on Code","author":"Chen","year":"2021","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2024.100943_bib53","article-title":"Judging LLM-as-a-judge with MT-bench and Chatbot Arena","author":"Zheng","year":"2023","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2024.100943_bib54","article-title":"QLoRA: Efficient Finetuning of Quantized LLMs","author":"Dettmers","year":"2023","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2024.100943_bib55","series-title":"Falcon-40B: an open large language model with state-of-the-art performance","author":"Almazrouei","year":"2023"},{"key":"10.1016\/j.patter.2024.100943_bib56","series-title":"Introducing Mpt-30b: Raising the Bar for Open-Source Foundation Models","author":"Team","year":"2023"},{"key":"10.1016\/j.patter.2024.100943_bib57","article-title":"GPT-NeoX-20B: An Open-source Autoregressive Language Model","author":"Black","year":"2022","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2024.100943_bib58","article-title":"LinkBERT: Pretraining Language Models with Document Links","author":"Yasunaga","year":"2022","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2024.100943_bib59","article-title":"Dense Passage Retrieval for Open-domain Question Answering","author":"Karpukhin","year":"2020","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2024.100943_bib60","article-title":"Training Verifiers to Solve Math Word Problems","author":"Cobbe","year":"2021","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2024.100943_bib61","article-title":"Language Models (Mostly) Know What They Know","author":"Kadavath","year":"2022","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2024.100943_bib62","article-title":"LIMA: Less Is More for Alignment","author":"Zhou","year":"2023","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2024.100943_bib63","article-title":"Towards Expert-level Medical Question Answering with Large Language Models","author":"Singhal","year":"2023","journal-title":"arXiv"}],"container-title":["Patterns"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2666389924000424?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2666389924000424?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T23:52:01Z","timestamp":1762991521000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S2666389924000424"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3]]},"references-count":63,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,3]]}},"alternative-id":["S2666389924000424"],"URL":"https:\/\/doi.org\/10.1016\/j.patter.2024.100943","relation":{},"ISSN":["2666-3899"],"issn-type":[{"value":"2666-3899","type":"print"}],"subject":[],"published":{"date-parts":[[2024,3]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Can large language models reason about medical questions?","name":"articletitle","label":"Article Title"},{"value":"Patterns","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patter.2024.100943","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2024 The Authors.","name":"copyright","label":"Copyright"}],"article-number":"100943"}}