{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T21:01:39Z","timestamp":1790888499927,"version":"4.1.0"},"reference-count":31,"publisher":"Oxford University Press (OUP)","issue":"10","license":[{"start":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T00:00:00Z","timestamp":1785801600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01AG073435"],"award-info":[{"award-number":["R01AG073435"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01LM013519"],"award-info":[{"award-number":["R01LM013519"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01AG080429"],"award-info":[{"award-number":["R01AG080429"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["1K99LM01402"],"award-info":[{"award-number":["1K99LM01402"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["1K99LM014614-01"],"award-info":[{"award-number":["1K99LM014614-01"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,10,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>Accurate citation of relevant publications is essential for scientific integrity in biomedical research. Large language models (LLMs) excel at text generation but often hallucinate fabricated or inaccurate citations. Retrieval-augmented generation (RAG) can mitigate these errors, yet current approaches lack semantic precision in evidence retrieval. This study aims to develop a domain-specific RAG system for reliable, context-specific biomedical citation recommendations.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and Methods<\/jats:title>\n                    <jats:p>We introduce CiteSure, a sentence-level citation recommendation tool designed to deliver reliable, evidence-based, and context-specific references using LLMs. CiteSure utilizes a 2-stage retrieval-augmented generation (RAG) framework, combining a domain-specific dense retriever (BioLLM2Vec) and reranker (BioRankLLaMA), adapted from LLaMA3-8B-Instruct using biomedical-specific training data. CiteSure leverages the complementary strengths of retrieval and generative LLM models, ensuring factual precision and contextual alignment. We evaluated CiteSure on a curated Alzheimer\u2019s disease dataset, comparing it to standalone LLMs and traditional retrieval-based methods.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>CiteSure achieved 100% factual accuracy and the highest relevance score of 77.50%, outperforming all baselines. BioLLM2Vec retrieved relevant articles with over 80% accuracy in the top 100 candidates. BioRankLLaMA consistently outperformed baseline rerankers across MAP, MRR, and Precision@5 metrics, confirming the benefit of domain-specific adaptation and contrastive fine-tuning.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion and Conclusion<\/jats:title>\n                    <jats:p>Our results demonstrate that CiteSure, built on a 2-stage retrieval-augmented generation framework, effectively integrates domain-specific retrieval with LLM-based generation to achieve substantial improvements over baseline approaches. Our work underscores the importance of domain-specific adaptation in biomedical citation recommendation and provides publicly available datasets, models, and code for support future research.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/jamia\/ocag122","type":"journal-article","created":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T11:47:07Z","timestamp":1783424827000},"page":"1934-1942","source":"Crossref","is-referenced-by-count":0,"title":["CiteSure: retrieval-augmented large language models for faithful biomedical citation recommendation"],"prefix":"10.1093","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9588-7454","authenticated-orcid":false,"given":"Qianqian","family":"Xie","sequence":"first","affiliation":[{"name":"Department of Biomedical Informatics and Data Science, School of Medicine, Yale University , New Haven, CT, 06510,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jeffrey","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics and Data Science, School of Medicine, Yale University , New Haven, CT, 06510,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1036-9365","authenticated-orcid":false,"given":"Yan","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics and Data Science, School of Medicine, Yale University , New Haven, CT, 06510,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jimin","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics and Data Science, School of Medicine, Yale University , New Haven, CT, 06510,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fongci","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics and Data Science, School of Medicine, Yale University , New Haven, CT, 06510,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruey-Ling","family":"Weng","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics and Data Science, School of Medicine, Yale University , New Haven, CT, 06510,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huan","family":"He","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics and Data Science, School of Medicine, Yale University , New Haven, CT, 06510,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingyu","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics and Data Science, School of Medicine, Yale University , New Haven, CT, 06510,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5274-4672","authenticated-orcid":false,"given":"Hua","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics and Data Science, School of Medicine, Yale University , New Haven, CT, 06510,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,8,4]]},"reference":[{"key":"2026100116361582200_ocag122-B1","doi-asserted-by":"crossref","first-page":"570","DOI":"10.1002\/asi.24750","article-title":"Chatgpt and a new academic reality: Artificial intelligence-written research papers and the ethics of the large language models in scholarly publishing","volume":"74","author":"Lund","year":"2023","journal-title":"Asso Info Sci Tech"},{"key":"2026100116361582200_ocag122-B2","doi-asserted-by":"crossref","first-page":"103141","DOI":"10.1016\/j.jbi.2019.103141","article-title":"A survey on literature based discovery approaches in biomedical domain","volume":"93","author":"Gopalakrishnan","year":"2019","journal-title":"J Biomed Inform"},{"key":"2026100116361582200_ocag122-B3","doi-asserted-by":"crossref","first-page":"baq036","DOI":"10.1093\/database\/baq036","article-title":"Pubmed and beyond: a survey of web tools for searching biomedical literature","volume":"2011","author":"Lu","year":"2011","journal-title":"Database (Oxford)"},{"key":"2026100116361582200_ocag122-B4","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1007\/978-1-4939-0709-0_2","volume-title":"Biomedical literature Mining","author":"Khare","year":"2014"},{"key":"2026100116361582200_ocag122-B5","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1197\/jamia.M1608","article-title":"Answering physicians\u2019 clinical questions: obstacles and potential solutions","volume":"12","author":"Ely","year":"2005","journal-title":"J Am Med Inform Assoc"},{"key":"2026100116361582200_ocag122-B6","author":"Hurst","year":"2024"},{"key":"2026100116361582200_ocag122-B7","author":"Nori","year":"2023"},{"key":"2026100116361582200_ocag122-B8","doi-asserted-by":"crossref","first-page":"24824","DOI":"10.52202\/068431-1800","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":"2026100116361582200_ocag122-B9","doi-asserted-by":"crossref","first-page":"152","DOI":"10.1016\/j.bbi.2023.02.022","article-title":"A chat (gpt) about the future of scientific publishing","volume":"110","author":"Hill-Yardin","year":"2023","journal-title":"Brain Behav Immun"},{"key":"2026100116361582200_ocag122-B10","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1016\/j.ajog.2023.04.004","article-title":"Beware of references when using chatgpt as a source of information to write scientific articles","volume":"229","author":"Sanchez-Ramos","year":"2023","journal-title":"Am. J. Obstet. Gynecol"},{"key":"2026100116361582200_ocag122-B11","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s10439-023-03248-4","article-title":"In reference to \u201crole of chat gpt in public health,\u201d to highlight the ai\u2019s incorrect reference generation","volume":"51","author":"Frosolini","year":"2023","journal-title":"Annals Biomed. Eng"},{"key":"2026100116361582200_ocag122-B12","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1080\/00330124.2023.2190373","article-title":"A preliminary investigation of fake peer-reviewed citations and references generated by chatgpt","volume":"75","author":"Day","year":"2023","journal-title":"The Prof. Geogr"},{"key":"2026100116361582200_ocag122-B13","first-page":"e39238","article-title":"High rates of fabricated and inaccurate references in chatgpt-generated medical content","volume":"15","author":"Bhattacharyya","year":"2023","journal-title":"Cureus"},{"key":"2026100116361582200_ocag122-B14","doi-asserted-by":"crossref","first-page":"104769","DOI":"10.1016\/j.jbi.2024.104769","article-title":"Biomedrag: A retrieval augmented large language model for biomedicine","volume":"162","author":"Li","year":"2025","journal-title":"J Biomed Inform"},{"key":"2026100116361582200_ocag122-B15","author":"Xiong","year":"2024"},{"key":"2026100116361582200_ocag122-B16"},{"key":"2026100116361582200_ocag122-B17","author":"Zhang","year":"2023"},{"key":"2026100116361582200_ocag122-B18"},{"key":"2026100116361582200_ocag122-B19","author":"Dubey","year":"2024"},{"key":"2026100116361582200_ocag122-B20"},{"key":"2026100116361582200_ocag122-B21","author":"Jin","year":"2023"},{"key":"2026100116361582200_ocag122-B22","author":"Ma","year":"2024"},{"key":"2026100116361582200_ocag122-B23","author":"Gao","year":"2023"},{"key":"2026100116361582200_ocag122-B24","doi-asserted-by":"crossref","first-page":"124456","DOI":"10.1016\/j.eswa.2024.124456","article-title":"Factual consistency evaluation of summarisation in the era of large language models","volume":"254","author":"Luo","year":"2024","journal-title":"Expert. Syst. Appl"},{"key":"2026100116361582200_ocag122-B25","first-page":"442"},{"key":"2026100116361582200_ocag122-B26","author":"Chen","year":"2019"},{"key":"2026100116361582200_ocag122-B27","author":"Nogueira","year":"2019"},{"key":"2026100116361582200_ocag122-B28","first-page":"708"},{"key":"2026100116361582200_ocag122-B29","volume-title":"Information Retrieval: A Health and Biomedical Perspective","author":"Hersh","year":"2003"},{"key":"2026100116361582200_ocag122-B30","volume-title":"Prabhakar Raghavan, and Hinrich Sch\u00fctze. Introduction to Information Retrieval","author":"Manning","year":"2008"},{"key":"2026100116361582200_ocag122-B31","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-02276-0","volume-title":"Information Retrieval Evaluation","author":"Harman","year":"2011"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jamia\/advance-article-pdf\/doi\/10.1093\/jamia\/ocag122\/70483457\/ocag122.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/33\/10\/1934\/70483457\/ocag122.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/33\/10\/1934\/70483457\/ocag122.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T20:36:27Z","timestamp":1790886987000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/33\/10\/1934\/8751307"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,4]]},"references-count":31,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2026,8,4]]},"published-print":{"date-parts":[[2026,10,1]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocag122","relation":{},"ISSN":["1067-5027","1527-974X"],"issn-type":[{"value":"1067-5027","type":"print"},{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,10]]},"published":{"date-parts":[[2026,8,4]]}}}