{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T07:21:01Z","timestamp":1780557661849,"version":"3.54.1"},"reference-count":187,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"Institute of Advance Research, United International University"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3365742","type":"journal-article","created":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T18:56:44Z","timestamp":1707850604000},"page":"26839-26874","source":"Crossref","is-referenced-by-count":720,"title":["A Review on Large Language Models: Architectures, Applications, Taxonomies, Open Issues and Challenges"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-4793-5382","authenticated-orcid":false,"given":"Mohaimenul Azam Khan","family":"Raiaan","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, United International University, Dhaka, Bangladesh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2675-5471","authenticated-orcid":false,"given":"Md. Saddam Hossain","family":"Mukta","sequence":"additional","affiliation":[{"name":"LUT School of Engineering Sciences, Lappeenranta-Lahti University of Technology, Lappeenranta, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0787-5403","authenticated-orcid":false,"given":"Kaniz","family":"Fatema","sequence":"additional","affiliation":[{"name":"Faculty of Science and Technology, Charles Darwin University, Casuarina, NT, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nur Mohammad","family":"Fahad","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, United International University, Dhaka, Bangladesh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2007-5746","authenticated-orcid":false,"given":"Sadman","family":"Sakib","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, United International University, Dhaka, Bangladesh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7138-2331","authenticated-orcid":false,"given":"Most Marufatul Jannat","family":"Mim","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, United International University, Dhaka, Bangladesh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jubaer","family":"Ahmad","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, United International University, Dhaka, Bangladesh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0384-7616","authenticated-orcid":false,"given":"Mohammed Eunus","family":"Ali","sequence":"additional","affiliation":[{"name":"Department of CSE, Bangladesh University of Engineering and Technology (BUET), Dhaka, Bangladesh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7572-9750","authenticated-orcid":false,"given":"Sami","family":"Azam","sequence":"additional","affiliation":[{"name":"Faculty of Science and Technology, Charles Darwin University, Casuarina, NT, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"The Language Instinct: How the Mind Creates Language","author":"Pinker","year":"2003"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1126\/science.298.5598.1569"},{"key":"ref3","article-title":"A survey of large language models","author":"Zhao","year":"2023","journal-title":"arXiv:2303.18223"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1093\/mind\/LIX.236.433"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.230163"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3272228"},{"key":"ref7","first-page":"1","article-title":"Proceedings of the NAACL-HLT 2012 workshop: Will we ever really replace the N-gram model? On the future of language modeling for HLT","volume-title":"Proc. NAACL-HLT","author":"Ramabhadran"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-343"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref10","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI48211.2021.9434063"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i17.17744"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/d41586-023-00816-5"},{"key":"ref14","volume-title":"An Important Next Step on Our AI Journey","author":"Pichai","year":"2023"},{"key":"ref15","volume-title":"Alpaca: A Strong, Replicable Instruction-following Model","author":"Taori","year":"2023"},{"key":"ref16","article-title":"A bibliometric review of large language models research from 2017 to 2023","author":"Fan","year":"2023","journal-title":"arXiv:2304.02020"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3641289"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.67"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.lindif.2023.102274"},{"key":"ref20","article-title":"A survey on large language models: Applications, challenges, limitations, and practical usage","author":"Hadi","year":"2023","journal-title":"TechRxiv"},{"key":"ref21","volume-title":"Annual review of information science and technology","volume":"39","author":"Cronin","year":"2004"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-37591-1_6"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1515\/9783110867275.105"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1988.tb00232.x"},{"key":"ref25","first-page":"67","article-title":"Automatic speech recognition\u2014A brief history of the technology development","volume":"1","author":"Juang","year":"2005"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.techfore.2022.121559"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s00146-022-01494-z"},{"key":"ref28","volume-title":"Transfer Learning for Natural Language Processing","author":"Azunre","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2014.11.004"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-90055-7_21"},{"key":"ref31","article-title":"Google\u2019s neural machine translation system: Bridging the gap between human and machine translation","author":"Wu","year":"2016","journal-title":"arXiv:1609.08144"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CONIT51480.2021.9498485"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1177\/20539517211047734"},{"key":"ref34","article-title":"Exploring transformers in natural language generation: GPT, BERT, and XLNet","author":"Onat Topal","year":"2021","journal-title":"arXiv:2102.08036"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s42452-019-1765-9"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s12652-021-03439-8"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1108\/LHTN-01-2023-0009"},{"key":"ref39","volume-title":"Improving Language Understanding by Generative Pre-Training","author":"Radford","year":"2024"},{"key":"ref40","volume-title":"Attention Mechanism, Transformers, BERT, and GPT: Tutorial and Survey","author":"Ghojogh","year":"2024"},{"issue":"8","key":"ref41","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.3390\/bdcc7030124"},{"key":"ref43","article-title":"Megatron-LM: Training multi-billion parameter language models using model parallelism","author":"Shoeybi","year":"2019","journal-title":"arXiv:1909.08053"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4389233"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijsu.2021.105906"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.3115\/992424.992434"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1007"},{"key":"ref48","article-title":"Neural machine translation of rare words with subword units","author":"Sennrich","year":"2015","journal-title":"arXiv:1508.07909"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289079"},{"key":"ref50","article-title":"Generating long sequences with sparse transformers","author":"Child","year":"2019","journal-title":"arXiv:1904.10509"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(89)90020-8"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.5555\/3104322.3104425"},{"key":"ref53","article-title":"Gaussian error linear units (GELUs)","author":"Hendrycks","year":"2016","journal-title":"arXiv:1606.08415"},{"key":"ref54","article-title":"Root mean square layer normalization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Zhang"},{"key":"ref55","article-title":"BLOOM: A 176B-parameter open-access multilingual language model","volume-title":"arXiv:2211.05100","author":"Workshop"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref57","article-title":"Prefix-tuning: Optimizing continuous prompts for generation","author":"Lisa Li","year":"2021","journal-title":"arXiv:2101.00190"},{"key":"ref58","article-title":"Scaling instruction-finetuned language models","author":"Chung","year":"2022","journal-title":"arXiv:2210.11416"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.3390\/biomedicines11061566"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-03865-x"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.893"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21319"},{"key":"ref64","first-page":"21297","article-title":"SOFT: Softmax-free transformer with linear complexity","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Lu"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/s11023-020-09548-1"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688232"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1907.11692"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.437"},{"key":"ref69","article-title":"PaLM: Scaling language modeling with pathways","author":"Chowdhery","year":"2022","journal-title":"arXiv:2204.02311"},{"key":"ref70","article-title":"LaMDA: Language models for dialog applications","author":"Thoppilan","year":"2022","journal-title":"arXiv:2201.08239"},{"key":"ref71","article-title":"GLM-130B: An open bilingual pre-trained model","author":"Zeng","year":"2022","journal-title":"arXiv:2210.02414"},{"key":"ref72","article-title":"Scaling language models: Methods, analysis & insights from training gopher","author":"Rae","year":"2021","journal-title":"arXiv:2112.11446"},{"key":"ref73","first-page":"9","article-title":"Jurassic-1: Technical details and evaluation","volume":"1","author":"Lieber","year":"2021","journal-title":"White Paper. AI21 Labs"},{"key":"ref74","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:2201.11990"},{"key":"ref75","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref76","article-title":"Fine-tuning llama 2 large language models for detecting online sexual predatory chats and abusive texts","author":"Thi Nguyen","year":"2023","journal-title":"arXiv:2308.14683"},{"key":"ref77","article-title":"The RefinedWeb dataset for falcon LLM: Outperforming curated corpora with web data, and web data only","author":"Penedo","year":"2023","journal-title":"arXiv:2306.01116"},{"key":"ref78","article-title":"Training compute-optimal large language models","author":"Hoffmann","year":"2022","journal-title":"arXiv:2203.15556"},{"key":"ref79","article-title":"OPT: Open pre-trained transformer language models","author":"Zhang","year":"2022","journal-title":"arXiv:2205.01068"},{"key":"ref80","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Wei"},{"key":"ref81","article-title":"PanGu-\u03b1: Large-scale autoregressive pretrained Chinese language models with auto-parallel computation","author":"Zeng","year":"2021","journal-title":"arXiv:2104.12369"},{"key":"ref82","article-title":"A comprehensive overview of large language models","author":"Naveed","year":"2023","journal-title":"arXiv:2307.06435"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1356"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.146"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1126\/science.abq1158"},{"key":"ref86","article-title":"Audio captioning using pre-trained large-scale language model guided by audio-based similar caption retrieval","author":"Koizumi","year":"2020","journal-title":"arXiv:2012.07331"},{"key":"ref87","article-title":"Recommender systems in the era of large language models (LLMs)","author":"Fan","year":"2023","journal-title":"arXiv:2307.02046"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3082299"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.4"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.33682\/1dze-8739"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383557"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-023-10132-6"},{"key":"ref93","article-title":"Large language models empowered autonomous edge AI for connected intelligence","author":"Shen","year":"2023","journal-title":"arXiv:2307.02779"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.3390\/a15020071"},{"key":"ref95","article-title":"Instruction tuning with GPT-4","author":"Peng","year":"2023","journal-title":"arXiv:2304.03277"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-4808"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1016\/j.psychres.2023.115334"},{"key":"ref98","article-title":"Galactica: A large language model for science","author":"Taylor","year":"2022","journal-title":"arXiv:2211.09085"},{"key":"ref99","article-title":"GLU variants improve transformer","author":"Shazeer","year":"2020","journal-title":"arXiv:2002.05202"},{"key":"ref100","first-page":"5547","article-title":"GLaM: Efficient scaling of language models with mixture-of-experts","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Du"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.bigscience-1.9"},{"key":"ref102","article-title":"CodeGen: An open large language model for code with multi-turn program synthesis","author":"Nijkamp","year":"2022","journal-title":"arXiv:2203.13474"},{"key":"ref103","article-title":"Thinking fast and slow in large language models","author":"Hagendorff","year":"2022","journal-title":"arXiv:2212.05206"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1016\/j.iotcps.2023.04.003"},{"key":"ref105","article-title":"Performance comparison of large language models on VNHSGE English dataset: OpenAI chatGPT, Microsoft bing chat, and Google bard","author":"Dao","year":"2023","journal-title":"arXiv:2307.02288"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1002\/pra2.927"},{"key":"ref107","article-title":"XLNet: Generalized autoregressive pretraining for language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Yang"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1511"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i15.17625"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbac409"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.wmt-1.96"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.42"},{"key":"ref113","volume-title":"OpenAI","year":"2023"},{"key":"ref114","volume-title":"Huggingface","year":"2023"},{"key":"ref115","volume-title":"Google Cloud","year":"2023"},{"key":"ref116","volume-title":"Azure","year":"2023"},{"key":"ref117","volume-title":"IBM Watson Natural Language Understanding","year":"2023"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCI48352.2020.9104105"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1016\/j.simpat.2023.102754"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4842-8844-3_4"},{"key":"ref121","article-title":"On the robustness of ChatGPT: An adversarial and out-of-distribution perspective","author":"Wang","year":"2023","journal-title":"arXiv:2302.12095"},{"key":"ref122","article-title":"Evaluation of ChatGPT family of models for biomedical reasoning and classification","author":"Chen","year":"2023","journal-title":"arXiv:2304.02496"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1038\/s41368-023-00239-y"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1038\/s41523-023-00557-8"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-023-02448-8"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-021-00464-x"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.3389\/fpubh.2023.1166120"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.3390\/healthcare11060887"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1007\/s10916-023-01925-4"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pdig.0000198"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1145\/3458754"},{"key":"ref132","article-title":"Foresight-generative pretrained transformer (GPT) for modelling of patient timelines using EHRs","author":"Kraljevic","year":"2022","journal-title":"arXiv:2212.08072"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1007\/s40558-023-00248-x"},{"key":"ref134","article-title":"Temporal data meets LLM\u2014Explainable financial time series forecasting","author":"Yu","year":"2023","journal-title":"arXiv:2306.11025"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.3390\/logistics7020026"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1007\/s11023-022-09602-0"},{"key":"ref137","article-title":"Large language models: A comprehensive survey of its applications, challenges, limitations, and future prospects","author":"Hadi","year":"2023"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.3390\/educsci13040410"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijinfomgt.2023.102642"},{"key":"ref140","article-title":"A survey on GPT-3","author":"Zong","year":"2022","journal-title":"arXiv:2212.00857"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-819314-3.00005-7"},{"key":"ref142","article-title":"Clinical XLNet: Modeling sequential clinical notes and predicting prolonged mechanical ventilation","author":"Huang","year":"2019","journal-title":"arXiv:1912.11975"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.362"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.151"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4405389"},{"key":"ref146","article-title":"Embedding-based retrieval with LLM for effective agriculture information extracting from unstructured data","author":"Peng","year":"2023","journal-title":"arXiv:2308.03107"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4405391"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.3390\/fi15120372"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1493"},{"key":"ref150","article-title":"Unsupervised cross-lingual representation learning at scale","author":"Conneau","year":"2019","journal-title":"arXiv:1911.02116"},{"key":"ref151","article-title":"DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter","author":"Sanh","year":"2019","journal-title":"arXiv:1910.01108"},{"key":"ref152","article-title":"ALBERT: A lite BERT for self-supervised learning of language representations","author":"Lan","year":"2019","journal-title":"arXiv:1909.11942"},{"key":"ref153","article-title":"Man is to computer programmer as woman is to homemaker? Debiasing word embeddings","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Bolukbasi"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-demos.30"},{"key":"ref155","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. NIPS","author":"Brown"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btz682"},{"key":"ref157","article-title":"Faithful explanations of black-box NLP models using LLM-generated counterfactuals","author":"Gat","year":"2023","journal-title":"arXiv:2310.00603"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.96"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.3390\/jsan12040061"},{"key":"ref160","article-title":"Bootstrapping multilingual semantic parsers using large language models","author":"Awasthi","year":"2022","journal-title":"arXiv:2210.07313"},{"key":"ref161","article-title":"Harnessing LLMs in curricular design: Using GPT-4 to support authoring of learning objectives","author":"Sridhar","year":"2023","journal-title":"arXiv:2306.17459"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1109\/ICCECE51049.2023.10085092"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1038\/s41433-023-02759-7"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.4324\/9781315558325-4"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1111\/1748-8583.12524"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1016\/j.mlwa.2023.100508"},{"key":"ref167","article-title":"EcomGPT: Instruction-tuning large language models with chain-of-task tasks for e-commerce","author":"Li","year":"2023","journal-title":"arXiv:2308.06966"},{"key":"ref168","volume-title":"A taxonomy for deriving business insights from user-generated content","author":"Weingart"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-72188-6_2"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1016\/j.chb.2022.107540"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1021\/acs.est.3c01106"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1155\/2023\/8691095"},{"key":"ref173","article-title":"A short survey of viewing large language models in legal aspect","author":"Sun","year":"2023","journal-title":"arXiv:2303.09136"},{"key":"ref174","first-page":"24457","article-title":"Tuning language models as training data generators for augmentation-enhanced few-shot learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Meng"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21307"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1109\/ECCE57851.2023.10101527"},{"key":"ref177","article-title":"Bring your own data! Self-supervised evaluation for large language models","author":"Jain","year":"2023","journal-title":"arXiv:2306.13651"},{"key":"ref178","article-title":"A survey on model compression for large language models","author":"Zhu","year":"2023","journal-title":"arXiv:2308.07633"},{"key":"ref179","article-title":"MT5: A massively multilingual pre-trained text-to-text transformer","author":"Xue","year":"2020","journal-title":"arXiv:2010.11934"},{"key":"ref180","article-title":"Parallel context windows for large language models","author":"Ratner","year":"2022","journal-title":"arXiv:2212.10947"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1007\/s11127-023-01097-2"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1145\/3503488"},{"key":"ref183","article-title":"Low-parameter federated learning with large language models","author":"Jiang","year":"2023","journal-title":"arXiv:2307.13896"},{"key":"ref184","article-title":"Towards explainable and language-agnostic LLMs: Symbolic reverse engineering of language at scale","author":"Saba","year":"2023","journal-title":"arXiv:2306.00017"},{"key":"ref185","article-title":"Multimodal chain-of-thought reasoning in language models","author":"Zhang","year":"2023","journal-title":"arXiv:2302.00923"},{"key":"ref186","article-title":"Dynamic LLM-agent network: An LLM-agent collaboration framework with agent team optimization","author":"Liu","year":"2023","journal-title":"arXiv:2310.02170"},{"key":"ref187","article-title":"LLM platform security: Applying a systematic evaluation framework to OpenAI\u2019s ChatGPT plugins","author":"Iqbal","year":"2023","journal-title":"arXiv:2309.10254"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10380310\/10433480.pdf?arnumber=10433480","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T17:35:05Z","timestamp":1709228105000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10433480\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":187,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3365742","relation":{"has-preprint":[{"id-type":"doi","id":"10.36227\/techrxiv.24171183.v1","asserted-by":"object"}]},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}