{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T16:22:35Z","timestamp":1774369355126,"version":"3.50.1"},"reference-count":55,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T00:00:00Z","timestamp":1748304000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Comput. Sci."],"abstract":"<jats:p>Large language models, the innovative breakthrough taking the world by storm, have been applied in several fields, such as medicine, education, finance, and law. Moreover, large language models can integrate into those fields through their abilities in natural language processing, text generation, question answering, and several other use cases that benefit human interactions and decision-making. Furthermore, it is imperative to acknowledge the differences involved with large language models beyond their applications by considering aspects such as their types, setups, parameters, and performance. This could help us understand how each large language model could be utilized to its fullest extent for maximum benefit. In this systematic literature review, we explore each of these aspects in depth. Finally, we conclude with insights and future directions for advancing the efficiency and applicability of large language models.<\/jats:p>","DOI":"10.3389\/fcomp.2025.1523699","type":"journal-article","created":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T16:07:44Z","timestamp":1748362064000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["Evaluating large language models: a systematic review of efficiency, applications, and future directions"],"prefix":"10.3389","volume":"7","author":[{"given":"Yasmeen","family":"Saleh","sequence":"first","affiliation":[]},{"given":"Manar","family":"Abu Talib","sequence":"additional","affiliation":[]},{"given":"Qassim","family":"Nasir","sequence":"additional","affiliation":[]},{"given":"Fatima","family":"Dakalbab","sequence":"additional","affiliation":[]}],"member":"1965","published-online":{"date-parts":[[2025,5,27]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"278","DOI":"10.1016\/j.aiepr.2023.03.003","article-title":"Assessing the capabilities of ChatGPT to improve additive manufacturing troubleshooting","volume":"6","author":"Badini","year":"2023","journal-title":"Adv. Indust. Eng. Polymer Res."},{"key":"ref2","author":"Bender","year":"2021"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"1946","DOI":"10.1145\/3591300","article-title":"Prompting is programming: a query language for large language models","volume":"7","author":"Beurer-Kellner","year":"2023","journal-title":"Proc. ACM Program. Lang."},{"key":"ref4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/S10916-023-01925-4\/TABLES\/2","article-title":"Evaluating the feasibility of ChatGPT in healthcare: an analysis of multiple clinical and research scenarios","volume":"47","author":"Cascella","year":"2023","journal-title":"J. Med. Syst."},{"key":"ref5","author":"Chang","year":"2023"},{"key":"ref6","author":"Deng","year":"2023"},{"key":"ref7","author":"Di Fede","year":"2022"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"1098","DOI":"10.1111\/jerd.13046","article-title":"Implications of large language models such as ChatGPT for dental medicine","volume":"35","author":"Eggmann","year":"2023","journal-title":"J. Esthet. Restor. Dent."},{"key":"ref9","author":"Fan","year":"2024"},{"key":"ref10","author":"Fan","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/S13347-023-00621-Y\/FIGURES\/3","article-title":"AI as agency without intelligence: on ChatGPT, large language models, and other generative models","volume":"36","author":"Floridi","year":"2023","journal-title":"Philos. Technol."},{"key":"ref12","author":"H\u00e4m\u00e4l\u00e4inen","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1002\/EV.20556","article-title":"Large language model applications for evaluation: opportunities and ethical implications","volume":"2023","author":"Head","year":"2023","journal-title":"N. Dir. Eval."},{"key":"ref14","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1038\/s41368-023-00239-y","article-title":"ChatGPT for shaping the future of dentistry: the potential of multi-modal large language model","volume":"15","author":"Huang","year":"2023","journal-title":"Int. J. Oral Sci."},{"key":"ref15","author":"Jain","year":"2022"},{"key":"ref16","author":"Jiang","year":"2022"},{"key":"ref17","author":"Jo","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"129680","DOI":"10.1016\/j.surfcoat.2023.129680","article-title":"Generative pre-trained transformers (GPT) for surface engineering","volume":"466","author":"Kamnis","year":"2023","journal-title":"Surf. Coat. Technol."},{"key":"ref19","author":"Kang","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"102274","DOI":"10.1016\/j.lindif.2023.102274","article-title":"ChatGPT for good? On opportunities and challenges of large language models for education","volume":"103","author":"Kasneci","year":"2023","journal-title":"Learn. Individ. Differ."},{"key":"ref21","author":"Kim","year":"2021"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1007\/s12195-023-00761-3","article-title":"Can Bard, Google\u2019s experimental Chatbot based on the LaMDA large language model, help to analyze the gender and racial diversity of authors in your cited scientific references?","volume":"16","author":"King","year":"2023","journal-title":"Cell. Mol. Bioeng."},{"key":"ref23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3560815","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":"ref24","doi-asserted-by":"publisher","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":"J. Assoc. Inf. Sci. Technol."},{"key":"ref25","author":"Macneil","year":"2022"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1038\/s41415-023-6132-y","article-title":"Application ChatGPT in conducting systematic reviews and meta-analyses","volume":"235","author":"Mahuli","year":"2023","journal-title":"Br. Dent. J."},{"key":"ref27","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1186\/s13040-023-00339-9","article-title":"ChatGPT and large language models in academia: opportunities and challenges","volume":"16","author":"Meyer","year":"2023","journal-title":"BioData Mining"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1038\/s42256-023-00644-2","article-title":"Large language models challenge the future of higher education","volume":"5","author":"Milano","year":"2023","journal-title":"Nat. Mach. Intellig."},{"key":"ref29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3605943","article-title":"Recent advances in natural language processing via large pre-trained language models: a survey","volume":"56","author":"Min","year":"2023","journal-title":"ACM Comput. Surv."},{"key":"ref30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/S43681-023-00289-2","article-title":"Auditing large language models: a three-layered approach","volume":"1","author":"M\u00f6kander","year":"2023","journal-title":"AI Ethics"},{"key":"ref31","author":"Pan","year":"2023"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1080\/15265161.2023.2233356","article-title":"AUTOGEN: a personalized large language model for academic enhancement\u2014ethics and proof of principle","volume":"23","author":"Porsdam Mann","year":"2023","journal-title":"Am. J. Bioeth."},{"key":"ref33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/S13643-023-02243-Z\/PEER-REVIEW","article-title":"Are ChatGPT and large language models \u2018the answer\u2019 to bringing us closer to systematic review automation?","volume":"12","author":"Qureshi","year":"2023","journal-title":"Syst. Rev."},{"key":"ref34","doi-asserted-by":"publisher","first-page":"103858","DOI":"10.1016\/j.jnca.2024.103858","article-title":"AI-enhanced blockchain technology: a review of advancements and opportunities","volume":"225","author":"Ressi","year":"2024","journal-title":"J. Netw. Comput. Appl."},{"key":"ref35","author":"Reynolds","year":"2021"},{"key":"ref36","author":"Ross","year":"2023"},{"key":"ref37","author":"Sarsa","year":"2022"},{"key":"ref38","author":"Scells","year":"2023"},{"key":"ref39","doi-asserted-by":"publisher","first-page":"18253","DOI":"10.1109\/ACCESS.2025.3533217","article-title":"Exploring LLMs applications in law: a literature review on current legal NLP approaches","volume":"13","author":"Siino","year":"2025","journal-title":"IEEE Access"},{"key":"ref40","author":"Singh","year":"2023"},{"key":"ref41","doi-asserted-by":"publisher","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":"ref42","doi-asserted-by":"publisher","first-page":"1146","DOI":"10.1109\/TVCG.2022.3209479","article-title":"Interactive and visual prompt engineering for ad-hoc task adaptation with large language models","volume":"29","author":"Strobelt","year":"2023","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"ref43","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1007\/s12599-023-00795-x","article-title":"Welcome to the era of ChatGPT et al.: the prospects of large language models","volume":"65","author":"Teubner","year":"2023","journal-title":"Bus. Inf. Syst. Eng."},{"key":"ref44","doi-asserted-by":"publisher","first-page":"1050","DOI":"10.59287\/icaens.1127","article-title":"Creating large language model applications utilizing LangChain: a primer on developing LLM apps fast","volume":"1","author":"Topsakal","year":"2023","journal-title":"Int. Conf. Appl. Eng. Nat. Sci."},{"key":"ref45","doi-asserted-by":"publisher","first-page":"13309","DOI":"10.1111\/COGS.13309","article-title":"Do large language models know what humans know?","volume":"47","author":"Trott","year":"2023","journal-title":"Cogn. Sci."},{"key":"ref46","author":"Urban","year":"2023"},{"key":"ref47","author":"Vaithilingam","year":"2022"},{"key":"ref48","doi-asserted-by":"publisher","first-page":"7110","DOI":"10.1109\/JIOT.2021.3074382","article-title":"Toward accurate anomaly detection in industrial internet of things using hierarchical federated learning","volume":"9","author":"Wang","year":"2022","journal-title":"IEEE Internet Things J."},{"key":"ref49","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TITS.2021.3129417","article-title":"Heterogeneous Blockchain and AI-driven hierarchical trust evaluation for 5G-enabled intelligent transportation systems","volume":"24","author":"Wang","year":"2023","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref50","doi-asserted-by":"publisher","first-page":"14237","DOI":"10.1109\/JIOT.2020.3023588","article-title":"A secure data aggregation strategy in edge computing and Blockchain-empowered internet of things","volume":"9","author":"Wang","year":"2022","journal-title":"IEEE Internet Things J."},{"key":"ref51","author":"Wang","year":"2023"},{"key":"ref52","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1016\/J.JIIXD.2023.10.007","article-title":"Unveiling security, privacy, and ethical concerns of ChatGPT","volume":"2","author":"Wu","year":"2023","journal-title":"J. Inform. Intellig."},{"key":"ref53","author":"Wu","year":"2022"},{"key":"ref54","author":"Xu","year":"2022"},{"key":"ref55","author":"Zamfirescu-Pereira","year":"2023"}],"container-title":["Frontiers in Computer Science"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcomp.2025.1523699\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T16:07:45Z","timestamp":1748362065000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcomp.2025.1523699\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,27]]},"references-count":55,"alternative-id":["10.3389\/fcomp.2025.1523699"],"URL":"https:\/\/doi.org\/10.3389\/fcomp.2025.1523699","relation":{},"ISSN":["2624-9898"],"issn-type":[{"value":"2624-9898","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,27]]},"article-number":"1523699"}}