{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T14:58:05Z","timestamp":1786460285154,"version":"build-2736575974"},"reference-count":67,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T00:00:00Z","timestamp":1785196800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T00:00:00Z","timestamp":1786406400000},"content-version":"vor","delay-in-days":14,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Molde University College - Specialized University in Logistics"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>The rapid adoption of Large Language Models (LLMs) has led to their widespread use as a general-purpose, fast-deployment solution across a broad range of tasks. In healthcare settings, this trend has accelerated the replacement of task-specific models with large generative architectures, often without an assessment of their efficiency or suitability for structured information extraction. While transformer-based encoder models have long been established as reliable solutions for clinical Named Entity Recognition (NER) and Information Extraction (IE), the increasing reliance on LLMs raises concerns regarding computational cost, scalability, energy consumption, and practical deployment in resource- and privacy-constrained environments. This study aimed to critically evaluate the assumption that LLMs constitute a universally superior solution for clinical NER and IE, by systematically comparing encoder-based Language Models (LMs), and LLMs in terms of extraction performance, efficiency, deployment feasibility, and environmental impact. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA 2020) guidelines, a scoping literature review was conducted using Scopus and Web of Science, covering peer-reviewed studies published between 2022 and 2025. In addition, a proof-of-concept case study was performed on European Portuguese clinical notes, comparing a domain-adapted encoder model (MediAlbertina-1.5B) with quantized Llama-based LLMs executed locally under identical hardware conditions. Models were evaluated using micro-averaged precision, recall, and F1-score, together with runtime, estimated energy consumption, and CO\u2082 emissions. The literature review showed that LLMs and transformer-based architectures were the most frequently used even thought encoder-based and domain-adapted models often perform strongly in clinical NER, particularly when recall, structured output, and computational efficiency are important. The empirical case study showed a similar pattern: MediAlbertina-1.5B achieved the highest performance (micro-F1\u2009=\u20090.430), whereas all evaluated Llama variants obtained markedly lower F1-scores (\u2264\u20090.123) due to systematic under-extraction. Despite their lower performance, the Llama models incurred 23\u201395\u2009\u00d7\u2009longer runtimes and one to two orders of magnitude higher estimated energy consumption and CO\u2082 emissions under the tested local CPU-only setup. In this proof-of-concept benchmark on 20 European Portuguese clinical reports, the domain-adapted MediAlbertina token-classification model achieved higher recall and micro-F1 than the evaluated locally executed, quantized Llama models. The Llama models were also substantially slower and less sustainable, with higher estimated energy use and CO\u2082 emissions under the tested hardware and prompting configuration. These findings suggest that domain-adapted encoder models may be preferable for similar structured clinical NER settings, although larger and externally validated benchmarks are needed before generalizing to other languages, clinical corpora, model families, or deployment environments.<\/jats:p>","DOI":"10.1038\/s41598-026-62884-7","type":"journal-article","created":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T08:10:35Z","timestamp":1785226235000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Domain-specific versus general large language models: a review and empirical benchmark in real medical texts"],"prefix":"10.1038","volume":"16","author":[{"given":"Lu\u00eds B.","family":"Elvas","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carolina","family":"Carvalho","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,28]]},"reference":[{"issue":"326","key":"62884_CR1","doi-asserted-by":"publisher","first-page":"113975","DOI":"10.1016\/j.knosys.2025.113975","volume":"27","author":"DP Panagoulias","year":"2025","unstructured":"Panagoulias, D. P., Palamidas, A., Virvou, M. & Tsihrintzis, G. A. A framework for evaluation and requirement extraction for fine-tuning of Large Language Models in multimodal medical diagnosis. Knowl. Based Syst. 27(326), 113975. https:\/\/doi.org\/10.1016\/j.knosys.2025.113975 (2025).","journal-title":"Knowl. Based Syst."},{"key":"62884_CR2","doi-asserted-by":"publisher","DOI":"10.3390\/bdcc9080198","author":"R Lai","year":"2025","unstructured":"Lai, R. et al. LAI: Label annotation interaction-based representation enhancement for end to end relation extraction. Big Data Cognitive Comput. https:\/\/doi.org\/10.3390\/bdcc9080198 (2025).","journal-title":"Big Data Cognitive Comput."},{"key":"62884_CR3","doi-asserted-by":"publisher","DOI":"10.3390\/app15115801","author":"C Zhou","year":"2025","unstructured":"Zhou, C., Huang, B. & Ling, Y. A Chinese few-shot named-entity recognition model based on multi-label prompts and boundary information. Appl. Sci. https:\/\/doi.org\/10.3390\/app15115801 (2025).","journal-title":"Appl. Sci."},{"key":"62884_CR4","doi-asserted-by":"publisher","first-page":"141036","DOI":"10.1109\/ACCESS.2023.3341612","volume":"11","author":"E Kim","year":"2023","unstructured":"Kim, E., Jeong, Y. & Choi, M.-S. MediBioDeBERTa: Biomedical language model with continuous learning and intermediate fine-tuning. IEEE Access 11, 141036\u2013141044. https:\/\/doi.org\/10.1109\/ACCESS.2023.3341612 (2023).","journal-title":"IEEE Access"},{"key":"62884_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2023.104400","author":"H Schafer","year":"2022","unstructured":"Schafer, H. et al. Medication event extraction in clinical notes: Contribution of the WisPerMed team to the n2c2 2022 challenge. J. Biomed. Inform. https:\/\/doi.org\/10.1016\/j.jbi.2023.104400 (2022).","journal-title":"J. Biomed. Inform."},{"key":"62884_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.109233","author":"MB Nunes","year":"2024","unstructured":"Nunes, M. B., Bone, J., Ferreira, J. C., Chaves, P. L. & Elvas, L. B. MediAlbertina: An European Portuguese medical language model. Comput. Biol. Med. https:\/\/doi.org\/10.1016\/j.compbiomed.2024.109233 (2024).","journal-title":"Comput. Biol. Med."},{"key":"62884_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2021.103970","author":"S Farnsworth","year":"2022","unstructured":"Farnsworth, S. et al. Extracting experimental parameter entities from scientific articles. J. Biomed. Inform. https:\/\/doi.org\/10.1016\/j.jbi.2021.103970 (2022).","journal-title":"J. Biomed. Inform."},{"issue":"2","key":"62884_CR8","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1007\/s10506-023-09388-1","volume":"33","author":"V Oliveira","year":"2025","unstructured":"Oliveira, V., Nogueira, G., Faleiros, T. & Marcacini, R. Combining prompt-based language models and weak supervision for labeling named entity recognition on legal documents. Artif. Intell. Law 33(2), 361\u2013381. https:\/\/doi.org\/10.1007\/s10506-023-09388-1 (2025).","journal-title":"Artif. Intell. Law"},{"key":"62884_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2025.104896","author":"H Liu","year":"2025","unstructured":"Liu, H. et al. Resource-efficient instruction tuning of large language models for biomedical named entity recognition. J. Biomed. Inform. https:\/\/doi.org\/10.1016\/j.jbi.2025.104896 (2025).","journal-title":"J. Biomed. Inform."},{"key":"62884_CR10","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-025-03071-y","author":"E Alleva","year":"2025","unstructured":"Alleva, E. et al. Keyword-optimized template insertion for clinical note classification via prompt-based learning. BMC Med. Inform. Decis. Mak. https:\/\/doi.org\/10.1186\/s12911-025-03071-y (2025).","journal-title":"BMC Med. Inform. Decis. Mak."},{"issue":"2","key":"62884_CR11","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1007\/s41666-025-00190-z","volume":"9","author":"DS Vithanage","year":"2025","unstructured":"Vithanage, D. S. et al. Adapting generative large language models for information extraction from unstructured electronic health records in residential aged care: A comparative analysis of training approaches. J. Healthc. Inform. Res. 9(2), 191\u2013219. https:\/\/doi.org\/10.1007\/s41666-025-00190-z (2025).","journal-title":"J. Healthc. Inform. Res."},{"key":"62884_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2024.103007","author":"O Rohanian","year":"2024","unstructured":"Rohanian, O. et al. Exploring the effectiveness of instruction tuning in biomedical language processing. Artif. Intell. Med. https:\/\/doi.org\/10.1016\/j.artmed.2024.103007 (2024).","journal-title":"Artif. Intell. Med."},{"key":"62884_CR13","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-15203-5","author":"S Chakraborty","year":"2025","unstructured":"Chakraborty, S., Chowdhury, R., Shuvo, S. R., Chatterjee, R. & Roy, S. A scalable framework for evaluating multiple language models through cross-domain generation and hallucination detection. Sci. Rep. https:\/\/doi.org\/10.1038\/s41598-025-15203-5 (2025).","journal-title":"Sci. Rep."},{"key":"62884_CR14","doi-asserted-by":"publisher","DOI":"10.2196\/73486","author":"H-Y Hsu","year":"2025","unstructured":"Hsu, H.-Y., Chen, L.-W., Hsu, W.-T., Hsieh, Y.-W. & Chang, S.-S. Extracting clinical guideline information using two large language models: Evaluation study. J. Med. Internet Res. https:\/\/doi.org\/10.2196\/73486 (2025).","journal-title":"J. Med. Internet Res."},{"key":"62884_CR15","doi-asserted-by":"publisher","unstructured":"Y. Ma, Y. Cao, Y. Hong, and A. Sun, Large Language Model Is Not a Good Few-shot Information Extractor, but a Good Reranker for Hard Samples!. 2023, https:\/\/doi.org\/10.48550\/ARXIV.2303.08559.","DOI":"10.48550\/ARXIV.2303.08559"},{"key":"62884_CR16","doi-asserted-by":"publisher","DOI":"10.3346\/jkms.2024.39.e291","author":"D Choi","year":"2024","unstructured":"Choi, D. et al. Using large language models to extract core injury information from emergency department notes. J. KOREAN Med. Sci. https:\/\/doi.org\/10.3346\/jkms.2024.39.e291 (2024).","journal-title":"J. KOREAN Med. Sci."},{"key":"62884_CR17","doi-asserted-by":"publisher","DOI":"10.1093\/jamiaopen\/ooaf109","author":"L Builtjes","year":"2025","unstructured":"Builtjes, L., Bosma, J., Prokop, M., van Ginneken, B. & Hering, A. Leveraging open-source large language models for clinical information extraction in resource-constrained settings. JAMIA OPEN https:\/\/doi.org\/10.1093\/jamiaopen\/ooaf109 (2025).","journal-title":"JAMIA OPEN"},{"key":"62884_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2025.110665","author":"K Arzideh","year":"2025","unstructured":"Arzideh, K. et al. From BERT to generative AI\u2014Comparing encoder-only vs. large language models in a cohort of lung cancer patients for named entity recognition in unstructured medical reports. Comput. Biol. Med. https:\/\/doi.org\/10.1016\/j.compbiomed.2025.110665 (2025).","journal-title":"Comput. Biol. Med."},{"key":"62884_CR19","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2025.103165","author":"N Isaradech","year":"2025","unstructured":"Isaradech, N., Riedel, A., Sirikul, W., Kreuzthaler, M. & Schulz, S. Zero- and few-shot named entity recognition and text expansion in medication prescriptions using large language models. Artif. Intell. Med. https:\/\/doi.org\/10.1016\/j.artmed.2025.103165 (2025).","journal-title":"Artif. Intell. Med."},{"issue":"4","key":"62884_CR20","doi-asserted-by":"publisher","first-page":"1873","DOI":"10.1021\/acs.jcim.4c00857","volume":"65","author":"P Kumar","year":"2025","unstructured":"Kumar, P., Kabra, S. & Cole, J. M. MechBERT: Language models for extracting chemical and property relationships about mechanical stress and strain. J. Chem. Inf. Model. 65(4), 1873\u20131888. https:\/\/doi.org\/10.1021\/acs.jcim.4c00857 (2025).","journal-title":"J. Chem. Inf. Model."},{"key":"62884_CR21","doi-asserted-by":"publisher","unstructured":"P. Belcak et al., Small Language Models are the Future of Agentic AI. 2025, arXiv. https:\/\/doi.org\/10.48550\/ARXIV.2506.02153.","DOI":"10.48550\/ARXIV.2506.02153"},{"key":"62884_CR22","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.n71","author":"MJ Page","year":"2020","unstructured":"Page, M. J. et al. The PRISMA 2020 statement: An updated guideline for reporting systematic reviews. BMJ https:\/\/doi.org\/10.1136\/bmj.n71 (2020).","journal-title":"BMJ"},{"key":"62884_CR23","unstructured":"\u201cScopus\u2014Homepage.\u201d Accessed: 02 Feb 2026. [Online]. Available: https:\/\/www.scopus.com\/pages\/home?display=basic#basic."},{"key":"62884_CR24","unstructured":"Document Search\u2014Web of Science Core Collection. Accessed: 02 Feb. 2026. [Online]. Available: https:\/\/www.webofscience.com\/wos\/woscc\/basic-search."},{"issue":"1","key":"62884_CR25","doi-asserted-by":"publisher","DOI":"10.1186\/s12874-018-0611-x","volume":"18","author":"Z Munn","year":"2018","unstructured":"Munn, Z. et al. Systematic review or scoping review? Guidance for authors when choosing between a systematic or scoping review approach. BMC Med. Res. Methodol. 18(1), 143. https:\/\/doi.org\/10.1186\/s12874-018-0611-x (2018).","journal-title":"BMC Med. Res. Methodol."},{"key":"62884_CR26","unstructured":"PubMed, PubMed. Accessed: 03 Feb 2026. [Online]. Available: https:\/\/pubmed.ncbi.nlm.nih.gov\/."},{"key":"62884_CR27","unstructured":"arXiv.org e-Print archive. Accessed: 03 Feb 2026. [Online]. Available: https:\/\/arxiv.org\/."},{"key":"62884_CR28","unstructured":"ACL Anthology. Accessed: 03 Feb. 2026. [Online]. Available: https:\/\/aclanthology.org\/."},{"key":"62884_CR29","unstructured":"Publications & Research | IEEE. Accessed: Feb. 03, 2026. [Online]. Available: https:\/\/www.ieee.org\/publications-research."},{"key":"62884_CR30","unstructured":"\u201cOpenAI.\u201d Accessed: Feb. 16, 2026. [Online]. Available: https:\/\/openai.com\/pt-PT\/."},{"key":"62884_CR31","unstructured":"Meta AI. Accessed: Feb. 16, 2026. [Online Video]. Available: https:\/\/www.meta.ai\/."},{"key":"62884_CR32","unstructured":"\u201cModel Cards.\u201d Accessed: Feb. 16, 2026. [Online]. Available: https:\/\/huggingface.co\/docs\/hub\/model-cardsv"},{"key":"62884_CR33","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2024.104731","author":"Y Yin","year":"2024","unstructured":"Yin, Y. et al. Augmenting biomedical named entity recognition with general-domain resources. J. Biomed. Inform. https:\/\/doi.org\/10.1016\/j.jbi.2024.104731 (2024).","journal-title":"J. Biomed. Inform."},{"key":"62884_CR34","doi-asserted-by":"publisher","DOI":"10.1101\/2025.05.19.654923","author":"L Busta","year":"2025","unstructured":"Busta, L. & Oyler, A. R. Small language models enable rapid and accurate extraction of structured data from unstructured text: An example with plants and their specialized metabolites. Plant Biol. https:\/\/doi.org\/10.1101\/2025.05.19.654923 (2025).","journal-title":"Plant Biol."},{"key":"62884_CR35","doi-asserted-by":"publisher","unstructured":"U. Zaratiana, N. Tomeh, P. Holat, and T. Charnois, \u201cGLiNER: Generalist Model for Named Entity Recognition using Bidirectional Transformer,\u201d 2023, arXiv. https:\/\/doi.org\/10.48550\/ARXIV.2311.08526.","DOI":"10.48550\/ARXIV.2311.08526"},{"key":"62884_CR36","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2023.104391","author":"Q Gan","year":"2023","unstructured":"Gan, Q. et al. A deep learning approach for medication disposition and corresponding attributes extraction. J. Biomed. Inform. https:\/\/doi.org\/10.1016\/j.jbi.2023.104391 (2023).","journal-title":"J. Biomed. Inform."},{"issue":"9","key":"62884_CR37","doi-asserted-by":"publisher","first-page":"1821","DOI":"10.1093\/jamia\/ocae122","volume":"31","author":"H Tran","year":"2024","unstructured":"Tran, H., Yang, Z., Yao, Z. & Yu, H. BioInstruct: Instruction tuning of large language models for biomedical natural language processing. J. Am. Med. Inform. Assoc. 31(9), 1821\u20131832. https:\/\/doi.org\/10.1093\/jamia\/ocae122 (2024).","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"62884_CR38","doi-asserted-by":"publisher","unstructured":"J. Boylan, C. Hokamp, and D. G. Ghalandari, GLiREL\u2014Generalist Model for Zero-Shot Relation Extraction. 2025, arXiv. https:\/\/doi.org\/10.48550\/ARXIV.2501.03172.","DOI":"10.48550\/ARXIV.2501.03172"},{"issue":"9","key":"62884_CR39","doi-asserted-by":"publisher","first-page":"1812","DOI":"10.1093\/jamia\/ocad259","volume":"31","author":"Y Hu","year":"2024","unstructured":"Hu, Y. et al. Improving large language models for clinical named entity recognition via prompt engineering. J. Am. Med. Inform. Assoc. 31(9), 1812\u20131820. https:\/\/doi.org\/10.1093\/jamia\/ocad259 (2024).","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"62884_CR40","doi-asserted-by":"publisher","unstructured":"I. Mouiche and S. Saad, TIJERE: A novel threat intelligence joint extraction model based on analyst expert knowledge. Knowl.-Based Syst., 2025, https:\/\/doi.org\/10.1016\/j.knosys.2025.114346.","DOI":"10.1016\/j.knosys.2025.114346"},{"issue":"2","key":"62884_CR41","doi-asserted-by":"publisher","first-page":"130","DOI":"10.3390\/info16020130","volume":"16","author":"H Allam","year":"2025","unstructured":"Allam, H., Makubvure, L., Gyamfi, B., Graham, K. N. & Akinwolere, K. Text classification: How machine learning is revolutionizing text categorization. Information 16(2), 130. https:\/\/doi.org\/10.3390\/info16020130 (2025).","journal-title":"Information"},{"key":"62884_CR42","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2024.102813","author":"L Cao","year":"2024","unstructured":"Cao, L., Wu, C., Luo, G., Guo, C. & Zheng, A. Online biomedical named entities recognition by data and knowledge-driven model. Artif. Intell. Med. https:\/\/doi.org\/10.1016\/j.artmed.2024.102813 (2024).","journal-title":"Artif. Intell. Med."},{"key":"62884_CR43","doi-asserted-by":"publisher","unstructured":"W. Xu, R. Dang, and S. Huang, \u201cLLM\u2019s Weakness in NER Doesn\u2019t Stop It from Enhancing a Stronger SLM,\u201d in Proceedings of the Second Workshop on Ancient Language Processing, The Albuquerque Convention Center, Laguna: Association for Computational Linguistics, 2025, pp. 170\u2013175. https:\/\/doi.org\/10.18653\/v1\/2025.alp-1.21.","DOI":"10.18653\/v1\/2025.alp-1.21"},{"key":"62884_CR44","doi-asserted-by":"publisher","DOI":"10.1038\/s40494-025-01624-y","author":"Q Xu","year":"2025","unstructured":"Xu, Q., Liu, Y., Wang, D. & Huang, S. Automatic recognition of cross-language classic entities based on large language models. Npj. Herit. Sci. https:\/\/doi.org\/10.1038\/s40494-025-01624-y (2025).","journal-title":"Npj. Herit. Sci."},{"key":"62884_CR45","doi-asserted-by":"publisher","DOI":"10.1016\/j.aei.2025.103134","author":"X Liao","year":"2025","unstructured":"Liao, X. et al. Large language model assisted fine-grained knowledge graph construction for robotic fault diagnosis. Adv. Eng. Inform. https:\/\/doi.org\/10.1016\/j.aei.2025.103134 (2025).","journal-title":"Adv. Eng. Inform."},{"issue":"12","key":"62884_CR46","doi-asserted-by":"publisher","first-page":"3267","DOI":"10.1093\/bioinformatics\/btac297","volume":"38","author":"L Lange","year":"2022","unstructured":"Lange, L., Adel, H., Str\u00f6tgen, J. & Klakow, D. CLIN-X: pre-trained language models and a study on cross-task transfer for concept extraction in the clinical domain. Bioinformatics 38(12), 3267\u20133274. https:\/\/doi.org\/10.1093\/bioinformatics\/btac297 (2022).","journal-title":"Bioinformatics"},{"key":"62884_CR47","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2025.110609","volume":"195","author":"A Bazoge","year":"2025","unstructured":"Bazoge, A. et al. Assessing large language models for acute heart failure classification and information extraction from French clinical notes. Comput. Biol. Med. 195, 110609. https:\/\/doi.org\/10.1016\/j.compbiomed.2025.110609 (2025).","journal-title":"Comput. Biol. Med."},{"issue":"4","key":"62884_CR48","doi-asserted-by":"publisher","first-page":"138","DOI":"10.35784\/acs-2024-44","volume":"20","author":"Z Kaddari","year":"2024","unstructured":"Kaddari, Z., Hachmi, I. E., Berrich, J., Amrani, R. & Bouchentouf, T. Evaluating large language models for medical information extraction: A comparative study of zero-shot and schema-based methods. Appl. Comput. Sci. 20(4), 138\u2013148. https:\/\/doi.org\/10.35784\/acs-2024-44 (2024).","journal-title":"Appl. Comput. Sci."},{"key":"62884_CR49","doi-asserted-by":"publisher","unstructured":"L. Li, L. Sleem, N. Gentile, G. Nichil, and R. State, Small Language Models in the Real World: Insights from Industrial Text Classification. 2025, arXiv. https:\/\/doi.org\/10.48550\/ARXIV.2505.16078.","DOI":"10.48550\/ARXIV.2505.16078"},{"key":"62884_CR50","doi-asserted-by":"publisher","first-page":"155031","DOI":"10.1109\/ACCESS.2025.3605709","volume":"13","author":"I Katranis","year":"2025","unstructured":"Katranis, I., Troussas, C., Krouska, A., Mylonas, P. & Sgouropoulou, C. Named entity recognition and news article classification: A lightweight approach. IEEE Access 13, 155031\u2013155046. https:\/\/doi.org\/10.1109\/ACCESS.2025.3605709 (2025).","journal-title":"IEEE Access"},{"issue":"3","key":"62884_CR51","doi-asserted-by":"publisher","first-page":"3243","DOI":"10.1007\/s10579-025-09834-3","volume":"59","author":"I Haq","year":"2025","unstructured":"Haq, I., Zhang, Y. & Qadri, I. A. POS tagging of low-resource Pashto language: Annotated corpus and BERT-based model. Lang. Resour. Eval. 59(3), 3243\u20133265. https:\/\/doi.org\/10.1007\/s10579-025-09834-3 (2025).","journal-title":"Lang. Resour. Eval."},{"key":"62884_CR52","doi-asserted-by":"publisher","unstructured":"B. Xu, Y. Chen, Z. Wen, W. Liu, and B. He, Evaluating Small Language Models for News Summarization: Implications and Factors Influencing Performance. 2025, arXiv. https:\/\/doi.org\/10.48550\/ARXIV.2502.00641.","DOI":"10.48550\/ARXIV.2502.00641"},{"issue":"9","key":"62884_CR53","doi-asserted-by":"publisher","first-page":"1929","DOI":"10.1093\/jamia\/ocae095","volume":"31","author":"M Li","year":"2024","unstructured":"Li, M., Zhou, H., Yang, H. & Zhang, R. RT: A retrieving and chain-of-thought framework for few-shot medical named entity recognition. J. Am. Med. Inform. Assoc. 31(9), 1929\u20131938. https:\/\/doi.org\/10.1093\/jamia\/ocae095 (2024).","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"62884_CR54","doi-asserted-by":"publisher","unstructured":"J. Zhu, S. Ozkan, A. Maracani, S. Mutlu, C. J. Min, and M. Ozay, Multi-Task Pre-Finetuning of Lightweight Transformer Encoders for Text Classification and NER. 2025, arXiv. https:\/\/doi.org\/10.48550\/ARXIV.2510.07566.","DOI":"10.48550\/ARXIV.2510.07566"},{"key":"62884_CR55","doi-asserted-by":"publisher","first-page":"718","DOI":"10.3233\/SHTI250934","volume":"329","author":"Y Hu","year":"2025","unstructured":"Hu, Y. et al. PheCatcher: Leveraging LLM-generated synthetic data for automated phenotype definition extraction from biomedical literature. Stud. Health Technol. Inform. 329, 718\u2013722. https:\/\/doi.org\/10.3233\/SHTI250934 (2025).","journal-title":"Stud. Health Technol. Inform."},{"key":"62884_CR56","doi-asserted-by":"publisher","DOI":"10.2196\/52095","author":"ZP Majdik","year":"2024","unstructured":"Majdik, Z. P. et al. Sample size considerations for fine-tuning large language models for named entity recognition tasks: Methodological study. JMIR AI https:\/\/doi.org\/10.2196\/52095 (2024).","journal-title":"JMIR AI"},{"key":"62884_CR57","doi-asserted-by":"publisher","unstructured":"T. M. Pham, P. T. Nguyen, S. Yoon, V. D. Lai, F. Dernoncourt, and T. Bui, SlimLM: An Efficient Small Language Model for On-Device Document Assistance. 2024, arXiv. https:\/\/doi.org\/10.48550\/ARXIV.2411.09944.","DOI":"10.48550\/ARXIV.2411.09944"},{"key":"62884_CR58","unstructured":"Detalhes do Projeto - Ci\u00eancia_Iscte - Iscte. Accessed: Feb. 02, 2026. [Online]. Available: https:\/\/ciencia.iscte-iul.pt\/projects\/aplicacoes-moveis-baseadas-em-inteligencia-artificial-para-resposta-de-saude-publica\/1567."},{"key":"62884_CR59","unstructured":"llama3.2. Accessed: Feb. 06, 2026. [Online]. Available: https:\/\/ollama.com\/llama3.2."},{"key":"62884_CR60","unstructured":"meta-llama\/Llama-3.2\u20133B-Instruct \u00b7 Hugging Face. Accessed: Feb. 06, 2026. [Online]. Available: https:\/\/huggingface.co\/meta-llama\/Llama-3.2-3B-Instruct."},{"key":"62884_CR61","unstructured":"llama3.1. Accessed: Feb. 06, 2026. [Online]. Available: https:\/\/ollama.com\/llama3.1."},{"key":"62884_CR62","unstructured":"meta-llama\/Llama-3.1\u20138B-Instruct \u00b7 Hugging Face. Accessed: Feb. 06, 2026. [Online]. Available: https:\/\/huggingface.co\/meta-llama\/Llama-3.1-8B-Instruct."},{"key":"62884_CR63","unstructured":"llama3.2:3b-instruct-q6_K. Accessed: Feb. 06, 2026. [Online]. Available: https:\/\/ollama.com\/llama3.2:3b-instruct-q6_K."},{"key":"62884_CR64","unstructured":"llama3.1:8b-instruct-q4_0. Accessed: Feb. 06, 2026. [Online]. Available: https:\/\/ollama.com\/llama3.1:8b-instruct-q4_0."},{"key":"62884_CR65","unstructured":"Intel\u00ae Celeron\u00ae Processor 7305 (8M Cache, 1.10 GHz) - Product Specifications. Intel. Accessed: Feb. 03, 2026. [Online]. Available: https:\/\/www.intel.com\/content\/www\/us\/en\/products\/sku\/226264\/intel-celeron-processor-7305-8m-cache-1-10-ghz\/specifications.html."},{"key":"62884_CR66","unstructured":"FATOR DE EMISS\u00c3O DA ELETRICIDADE 2025 PORTUGAL. Accessed: Feb. 03, 2026. [Online]. Available: https:\/\/apambiente.pt\/sites\/default\/files\/_Clima\/Inventarios\/20250808\/fe_gee_eletricidade_2025_final_apc.pdf."},{"key":"62884_CR67","unstructured":"UK Energy Statistics, 2012 Guidelines to Defra\/DECC\u2019s GHG Conversion Factors for Company Reporting, and Digest of UK Energy Statistics 2011 (DUKES)). 2011. Accessed: Jul. 03, 2026. [Online]. Available: https:\/\/assets.publishing.service.gov.uk\/media\/5a7987cee5274a684690a3ff\/7309-cca-draft-technical-guidance-app-b.xls."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-62884-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-62884-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-62884-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T12:41:05Z","timestamp":1786452065000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-62884-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,28]]},"references-count":67,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["62884"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-62884-7","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,28]]},"assertion":[{"value":"13 April 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 July 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 July 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Ethics"}}],"article-number":"24933"}}