{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T12:34:02Z","timestamp":1777379642014,"version":"3.51.4"},"reference-count":70,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T00:00:00Z","timestamp":1775520000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003086","name":"Government of the Basque Country","doi-asserted-by":"publisher","award":["ZE-2024\/00030"],"award-info":[{"award-number":["ZE-2024\/00030"]}],"id":[{"id":"10.13039\/501100003086","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Array"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.array.2026.100805","type":"journal-article","created":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T07:48:20Z","timestamp":1775634500000},"page":"100805","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Generative models for clinical entity linking in Spanish"],"prefix":"10.1016","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8350-1331","authenticated-orcid":false,"given":"Elena","family":"Zotova","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3620-1053","authenticated-orcid":false,"given":"Montse","family":"Cuadros","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1119-0930","authenticated-orcid":false,"given":"German","family":"Rigau","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"issue":"4","key":"10.1016\/j.array.2026.100805_b1","first-page":"188","article-title":"Charlson comorbidity index: ICD-9 update and ICD-10 translation","volume":"12","author":"Glasheen","year":"2019","journal-title":"Am Health & Drug Benefits"},{"key":"10.1016\/j.array.2026.100805_b2","series-title":"Proceedings of the 2020 conference on empirical methods in natural language processing","first-page":"6397","article-title":"Scalable zero-shot entity linking with dense entity retrieval","author":"Wu","year":"2020"},{"key":"10.1016\/j.array.2026.100805_b3","series-title":"8th international conference on learning representations, ICLR 2020","first-page":"1","article-title":"Poly-encoders: Architectures and pre-training strategies for fast and accurate multi-sentence scoring","author":"Humeau","year":"2020"},{"key":"10.1016\/j.array.2026.100805_b4","series-title":"Proceedings of the 57th annual meeting of the association for computational linguistics","first-page":"3449","article-title":"Zero-shot entity linking by reading entity descriptions","author":"Logeswaran","year":"2019"},{"key":"10.1016\/j.array.2026.100805_b5","series-title":"Proceedings of the 2020 conference on empirical methods in natural language processing","first-page":"6769","article-title":"Dense passage retrieval for open-domain question answering","author":"Karpukhin","year":"2020"},{"key":"10.1016\/j.array.2026.100805_b6","series-title":"ICD-10 : international statistical classification of diseases and related health problems : tenth revision","author":"World Health Organization (WHO)","year":"2004"},{"key":"10.1016\/j.array.2026.100805_b7","series-title":"eCIE-maps metasearch browser","author":"Ministry of Health of Spain","year":"2025"},{"key":"10.1016\/j.array.2026.100805_b8","series-title":"Proceedings of the 27th international conference on neural information processing systems - volume 2","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"Sutskever","year":"2014"},{"key":"10.1016\/j.array.2026.100805_b9","series-title":"Proceedings of the 2021 conference of the North American chapter of the association for computational linguistics: human language technologies","first-page":"483","article-title":"mT5: A massively multilingual pre-trained text-to-text transformer","author":"Xue","year":"2021"},{"key":"10.1016\/j.array.2026.100805_b10","series-title":"Proceedings of the 58th annual meeting of the association for computational linguistics","first-page":"7871","article-title":"BART: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension","author":"Lewis","year":"2020"},{"key":"10.1016\/j.array.2026.100805_b11","series-title":"Proceedings of the third workshop on natural language generation, evaluation, and metrics","first-page":"128","article-title":"Adapting pre-trained generative models for extractive question answering","author":"Mallick","year":"2023"},{"key":"10.1016\/j.array.2026.100805_b12","series-title":"Proceedings of the 16th conference of the European chapter of the association for computational linguistics: main volume","first-page":"874","article-title":"Leveraging passage retrieval with generative models for open domain question answering","author":"Izacard","year":"2021"},{"key":"10.1016\/j.array.2026.100805_b13","series-title":"Proceedings of the international conference on learning representations","first-page":"1","article-title":"Autoregressive entity retrieval","author":"De Cao","year":"2021"},{"key":"10.1016\/j.array.2026.100805_b14","doi-asserted-by":"crossref","first-page":"274","DOI":"10.1162\/tacl_a_00460","article-title":"Multilingual autoregressive entity linking","volume":"10","author":"De Cao","year":"2022","journal-title":"Trans Assoc Comput Linguist"},{"key":"10.1016\/j.array.2026.100805_b15","series-title":"Proceedings of the 17th conference of the European chapter of the association for computational linguistics","first-page":"2061","article-title":"ZELDA: A comprehensive benchmark for supervised entity disambiguation","author":"Milich","year":"2023"},{"key":"10.1016\/j.array.2026.100805_b16","series-title":"Proceedings of the 21st workshop on biomedical language processing","first-page":"97","article-title":"BioBART: Pretraining and evaluation of a biomedical generative language model","author":"Yuan","year":"2022"},{"key":"10.1016\/j.array.2026.100805_b17","series-title":"Proceedings of the 2022 conference of the North American chapter of the association for computational linguistics: human language technologies","first-page":"4038","article-title":"Generative biomedical entity linking via knowledge base-guided pre-training and synonyms-aware fine-tuning","author":"Yuan","year":"2022"},{"issue":"4","key":"10.1016\/j.array.2026.100805_b18","doi-asserted-by":"crossref","first-page":"281","DOI":"10.1055\/s-0038-1634945","article-title":"The unified medical language system","volume":"32","author":"Lindberg","year":"1993","journal-title":"Methods Inf Med"},{"key":"10.1016\/j.array.2026.100805_b19","series-title":"Proceedings of the 2023 conference on empirical methods in natural language processing","first-page":"5742","article-title":"Controllable contrastive generation for multilingual biomedical entity linking","author":"Zhu","year":"2023"},{"issue":"5","key":"10.1016\/j.array.2026.100805_b20","article-title":"Embracing large language models for medical applications: opportunities and challenges","volume":"15","author":"Karabacak","year":"2023","journal-title":"Cureus"},{"key":"10.1016\/j.array.2026.100805_b21","series-title":"Capabilities of GPT-4 on medical challenge problems","author":"Nori","year":"2023"},{"issue":"5","key":"10.1016\/j.array.2026.100805_b22","doi-asserted-by":"crossref","DOI":"10.1056\/AIoa2300151","article-title":"Comparative evaluation of LLMs in clinical oncology","volume":"1","author":"Rydzewski","year":"2024","journal-title":"NEJM AI"},{"key":"10.1016\/j.array.2026.100805_b23","article-title":"On the limitations of large language models in clinical diagnosis","author":"Reese","year":"2024","journal-title":"MedRxiv Prerint MedRxiv:2023.07.13.23292613"},{"issue":"5","key":"10.1016\/j.array.2026.100805_b24","doi-asserted-by":"crossref","DOI":"10.1056\/AIdbp2300040","article-title":"Large language models are poor medical coders \u2014 benchmarking of medical code querying","volume":"1","author":"Soroush","year":"2024","journal-title":"NEJM AI"},{"key":"10.1016\/j.array.2026.100805_b25","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.127241","article-title":"Contrastive learning with large language models for medical code prediction","volume":"277","author":"Wu","year":"2025","journal-title":"Expert Syst Appl"},{"key":"10.1016\/j.array.2026.100805_b26","series-title":"Proceedings of the 2023 conference on empirical methods in natural language processing","first-page":"2267","article-title":"Instructed language models with retrievers are powerful entity linkers","author":"Xiao","year":"2023"},{"key":"10.1016\/j.array.2026.100805_b27","doi-asserted-by":"crossref","DOI":"10.1016\/j.artmed.2024.102938","article-title":"MedExpQA: Multilingual benchmarking of large language models for medical question answering","volume":"155","author":"Alonso","year":"2024","journal-title":"Artif Intell Med"},{"key":"10.1016\/j.array.2026.100805_b28","series-title":"Proceedings of the 56th annual meeting of the association for computational linguistics (volume 1: long papers)","first-page":"328","article-title":"Universal language model fine-tuning for text classification","author":"Howard","year":"2018"},{"issue":"2","key":"10.1016\/j.array.2026.100805_b29","doi-asserted-by":"crossref","first-page":"270","DOI":"10.1162\/neco.1989.1.2.270","article-title":"A learning algorithm for continually running fully recurrent neural networks","volume":"1","author":"Williams","year":"1989","journal-title":"Neural Comput"},{"key":"10.1016\/j.array.2026.100805_b30","series-title":"Proceedings of the 36th international conference on neural information processing systems","first-page":"1","article-title":"Training language models to follow instructions with human feedback","author":"Ouyang","year":"2022"},{"key":"10.1016\/j.array.2026.100805_b31","series-title":"Proceedings of the 2020 conference on empirical methods in natural language processing: system demonstrations","first-page":"38","article-title":"Transformers: State-of-the-art natural language processing","author":"Wolf","year":"2020"},{"issue":"3","key":"10.1016\/j.array.2026.100805_b32","doi-asserted-by":"crossref","first-page":"535","DOI":"10.1109\/TBDATA.2019.2921572","article-title":"Billion-scale similarity search with GPUs","volume":"7","author":"Johnson","year":"2019","journal-title":"IEEE Trans Big Data"},{"key":"10.1016\/j.array.2026.100805_b33","series-title":"Advances in neural information processing systems","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020"},{"key":"10.1016\/j.array.2026.100805_b34","series-title":"Advances in neural information processing systems","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.array.2026.100805_b35","series-title":"Proceedings of the 1st international conference on data science and engineering (ICDSE 2024)","first-page":"524","article-title":"Comparative analysis of encoder-only, decoder-only, and encoder-decoder language models","author":"Liu","year":"2024"},{"key":"10.1016\/j.array.2026.100805_b36","series-title":"Proceedings of ACL-IJCNLP 2021","first-page":"565","article-title":"Learning domain-specialised representations for cross-lingual biomedical entity linking","author":"Liu","year":"2021"},{"key":"10.1016\/j.array.2026.100805_b37","series-title":"Working notes of conference and labs of the evaluation forum (CLEF). CEUR workshop proceedings","first-page":"1","article-title":"Overview of automatic clinical coding: annotations, guidelines, and solutions for non-english clinical cases at CodiEsp track of CLEF ehealth 2020","author":"Miranda-Escalada","year":"2020"},{"key":"10.1016\/j.array.2026.100805_b38","series-title":"cLiC-it","first-page":"258","article-title":"The E3C project: Collection and annotation of a multilingual corpus of clinical cases","author":"Magnini","year":"2020"},{"issue":"5","key":"10.1016\/j.array.2026.100805_b39","doi-asserted-by":"crossref","first-page":"948","DOI":"10.1093\/jamia\/ocv037","article-title":"A multilingual gold-standard corpus for biomedical concept recognition: the mantra GSC","volume":"22","author":"Kors","year":"2015","journal-title":"J Am Med Informatics Assoc"},{"key":"10.1016\/j.array.2026.100805_b40","article-title":"CT-EBM-SP - corpus of clinical trials for evidence-based-medicine in spanish","volume":"21","author":"Campillos-Llanos","year":"2021","journal-title":"BMC Med Inform Decis Mak"},{"key":"10.1016\/j.array.2026.100805_b41","series-title":"Proceedings of the thirteenth language resources and evaluation conference","first-page":"3661","article-title":"ClinIDMap: Towards a clinical IDs mapping for data interoperability","author":"Zotova","year":"2022"},{"issue":"4","key":"10.1016\/j.array.2026.100805_b42","doi-asserted-by":"crossref","first-page":"ooae118","DOI":"10.1093\/jamiaopen\/ooae118","article-title":"Implications of mappings between international classification of diseases clinical diagnosis codes and human phenotype ontology terms","volume":"7","author":"Tan","year":"2024","journal-title":"JAMIA Open"},{"key":"10.1016\/j.array.2026.100805_b43","series-title":"spaCy: Industrial-strength natural language processing in python","author":"Honnibal","year":"2020"},{"key":"10.1016\/j.array.2026.100805_b44","series-title":"Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing","first-page":"3982","article-title":"Sentence-BERT: Sentence embeddings using siamese BERT-networks","author":"Reimers","year":"2019"},{"key":"10.1016\/j.array.2026.100805_b45","series-title":"Biomedical and clinical language models for spanish: On the benefits of domain-specific pretraining in a mid-resource scenario","author":"Carrino","year":"2021"},{"key":"10.1016\/j.array.2026.100805_b46","series-title":"Proceedings of the 23rd conference on computational natural language learning","first-page":"528","article-title":"Learning dense representations for entity retrieval","author":"Gillick","year":"2019"},{"key":"10.1016\/j.array.2026.100805_b47","series-title":"Sentence transformers (SBERT) documentation","author":"Reimers","year":"2025"},{"key":"10.1016\/j.array.2026.100805_b48","series-title":"Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, volume 1 (long and short papers)","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"10.1016\/j.array.2026.100805_b49","doi-asserted-by":"crossref","first-page":"264","DOI":"10.1162\/tacl_a_00313","article-title":"Leveraging pre-trained checkpoints for sequence generation tasks","volume":"8","author":"Rothe","year":"2020","journal-title":"Trans Assoc Comput Linguist"},{"key":"10.1016\/j.array.2026.100805_b50","series-title":"Proceedings of the 21st workshop on biomedical language processing","first-page":"193","article-title":"Pretrained biomedical language models for clinical NLP in spanish","author":"Carrino","year":"2022"},{"key":"10.1016\/j.array.2026.100805_b51","series-title":"Proceedings of the 2024 joint international conference on computational linguistics, language resources and evaluation (LREC-cOLING 2024)","first-page":"11165","article-title":"MedMT5: An open-source multilingual text-to-text LLM for the medical domain","author":"Garc\u00eda-Ferrero","year":"2024"},{"key":"10.1016\/j.array.2026.100805_b52","series-title":"Multilingual translation with extensible multilingual pretraining and finetuning","author":"Tang","year":"2020"},{"key":"10.1016\/j.array.2026.100805_b53","series-title":"Proceedings of the 37th international conference on neural information processing systems","first-page":"1","article-title":"QLORA: efficient finetuning of quantized LLMs","author":"Dettmers","year":"2024"},{"issue":"9","key":"10.1016\/j.array.2026.100805_b54","doi-asserted-by":"crossref","first-page":"355","DOI":"10.3390\/info12090355","article-title":"Decoding methods in neural language generation: A survey","volume":"12","author":"Zarrie\u00df","year":"2021","journal-title":"Information"},{"key":"10.1016\/j.array.2026.100805_b55","series-title":"Text summarization branches out","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","author":"Lin","year":"2004"},{"key":"10.1016\/j.array.2026.100805_b56","series-title":"Proceedings of the 40th annual meeting of the association for computational linguistics","first-page":"311","article-title":"BLEU: a method for automatic evaluation of machine translation","author":"Papineni","year":"2002"},{"key":"10.1016\/j.array.2026.100805_b57","series-title":"Proceedings of the ACL workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","author":"Banerjee","year":"2005"},{"key":"10.1016\/j.array.2026.100805_b58","series-title":"SemScore: Automated evaluation of instruction-tuned LLMs based on semantic textual similarity","author":"Aynetdinov","year":"2024"},{"key":"10.1016\/j.array.2026.100805_b59","series-title":"International conference on learning representations","first-page":"1","article-title":"BERTScore: Evaluating text generation with BERT","author":"Zhang","year":"2020"},{"key":"10.1016\/j.array.2026.100805_b60","series-title":"International conference on learning representations","first-page":"1","article-title":"DEBERTA: decoding-enhanced BERT with disentangles attention","author":"He","year":"2021"},{"key":"10.1016\/j.array.2026.100805_b61","series-title":"Statistical methods in education and psychology","author":"Glass","year":"1996"},{"key":"10.1016\/j.array.2026.100805_b62","series-title":"Findings of the association for computational linguistics: EMNLP 2023","first-page":"1827","article-title":"Towards mitigating LLM hallucination via self reflection","author":"Ji","year":"2023"},{"issue":"2","key":"10.1016\/j.array.2026.100805_b63","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3703155","article-title":"A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions","volume":"43","author":"Huang","year":"2025","journal-title":"ACM Trans Inf Syst"},{"issue":"9","key":"10.1016\/j.array.2026.100805_b64","doi-asserted-by":"crossref","DOI":"10.3390\/ai6090226","article-title":"Retrieval-augmented generation (RAG) in healthcare: A comprehensive review","volume":"6","author":"Neha","year":"2025","journal-title":"AI"},{"issue":"9","key":"10.1016\/j.array.2026.100805_b65","doi-asserted-by":"crossref","first-page":"btae560","DOI":"10.1093\/bioinformatics\/btae560","article-title":"Biomedical knowledge graph-optimized prompt generation for large language models","volume":"40","author":"Soman","year":"2024","journal-title":"Bioinformatics"},{"issue":"2","key":"10.1016\/j.array.2026.100805_b66","doi-asserted-by":"crossref","DOI":"10.1056\/AIoa2300068","article-title":"Almanac \u2014 Retrieval-augmented language models for clinical medicine","volume":"1","author":"Zakka","year":"2024","journal-title":"NEJM AI"},{"key":"10.1016\/j.array.2026.100805_b67","series-title":"Proceedings of the 34th international conference on neural information processing systems","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive NLP tasks","author":"Lewis","year":"2020"},{"key":"10.1016\/j.array.2026.100805_b68","series-title":"Machine learning and knowledge discovery in databases. applied data science track","first-page":"215","article-title":"MedSyn: LLM-based synthetic medical text generation framework","author":"Kumichev","year":"2024"},{"issue":"10","key":"10.1016\/j.array.2026.100805_b69","doi-asserted-by":"crossref","first-page":"2284","DOI":"10.1093\/jamia\/ocae132","article-title":"Can GPT-3.5 generate and code discharge summaries?","volume":"31","author":"Falis","year":"2024","journal-title":"J Am Med Informatics Assoc"},{"key":"10.1016\/j.array.2026.100805_b70","series-title":"SEPLN-2024: 40th conference of the spanish society for natural language processing","first-page":"69","article-title":"Synthetic annotated data for named entity recognition in computed tomography scan reports","author":"Platas","year":"2024"}],"container-title":["Array"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2590005626001281?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2590005626001281?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T09:15:06Z","timestamp":1777367706000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S2590005626001281"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":70,"alternative-id":["S2590005626001281"],"URL":"https:\/\/doi.org\/10.1016\/j.array.2026.100805","relation":{},"ISSN":["2590-0056"],"issn-type":[{"value":"2590-0056","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Generative models for clinical entity linking in Spanish","name":"articletitle","label":"Article Title"},{"value":"Array","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.array.2026.100805","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier Inc.","name":"copyright","label":"Copyright"}],"article-number":"100805"}}