A Review on Large Language Models: Architectures, Applications, Taxonomies, Open Issues and Challenges

Large Language Models (LLMs) recently demonstrated extraordinary capability, including natural language processing (NLP), language translation, text generation, question answering, etc. Moreover, LLMs are a new and essential part of computerized language processing, having the ability to understand...

Full description

Saved in:

Bibliographic Details
Published in:	IEEE access Vol. 12; p. 1
Main Authors:	Raiaan, Mohaimenul Azam Khan, Mukta, Md. Saddam Hossain, Fatema, Kaniz, Fahad, Nur Mohammad, Sakib, Sadman, Mim, Most. Marufatul Jannat, Ahmad, Jubaer, Ali, Mohammed Eunus, Azam, Sami
Format:	Journal Article
Language:	English
Published:	Piscataway IEEE 01.01.2024 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:	Agriculture Application Artificial intelligence Automatic text generation Biomedicine Challenges Cognition Community research Computerization Evolution Health care Health services Information analysis Language Language modeling Language translation Large Language Models Large language models (LLM) Linguistics Natural language generation Natural language processing natural language processing (NLP) pre-trained models Pretrained models Question answering (information retrieval) Surveys Task analysis Taxonomy Training Transformer Transformers Translation World problems
ISSN:	2169-3536, 2169-3536
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	Large Language Models (LLMs) recently demonstrated extraordinary capability, including natural language processing (NLP), language translation, text generation, question answering, etc. Moreover, LLMs are a new and essential part of computerized language processing, having the ability to understand complex verbal patterns and generate coherent and appropriate replies for the situation. Though this success of LLMs has prompted a substantial increase in research contributions, rapid growth has made it difficult to understand the overall impact of these improvements. Since a lot of new research on LLMs is coming out quickly, it is getting tough to get an overview of all of them in a short note. Consequently, the research community would benefit from a short but thorough review of the recent changes in this area. This article thoroughly overviews LLMs, including their history, architectures, transformers, resources, training methods, applications, impacts, challenges, etc. This paper begins by discussing the fundamental concepts of LLMs with its traditional pipeline of the LLMs training phase. It then provides an overview of the existing works, the history of LLMs, their evolution over time, the architecture of transformers in LLMs, the different resources of LLMs, and the different training methods that have been used to train them. It also demonstrated the datasets utilized in the studies. After that, the paper discusses the wide range of applications of LLMs, including biomedical and healthcare, education, social, business, and agriculture. It also illustrates how LLMs create an impact on society and shape the future of AI and how they can be used to solve real-world problems. Then it also explores open issues and challenges to deploying LLMs in real-world scenario. Our review paper aims to help practitioners, researchers, and experts thoroughly understand the evolution of LLMs, pre-trained architectures, applications, challenges, and future goals.
AbstractList	Large Language Models (LLMs) recently demonstrated extraordinary capability in various natural language processing (NLP) tasks including language translation, text generation, question answering, etc. Moreover, LLMs are new and essential part of computerized language processing, having the ability to understand complex verbal patterns and generate coherent and appropriate replies in a given context. Though this success of LLMs has prompted a substantial increase in research contributions, rapid growth has made it difficult to understand the overall impact of these improvements. Since a plethora of research on LLMs have been appeared within a short time, it is quite impossible to track all of these and get an overview of the current state of research in this area. Consequently, the research community would benefit from a short but thorough review of the recent changes in this area. This article thoroughly overviews LLMs, including their history, architectures, transformers, resources, training methods, applications, impacts, challenges, etc. This paper begins by discussing the fundamental concepts of LLMs with its traditional pipeline of the LLMs training phase. Then the paper provides an overview of the existing works, the history of LLMs, their evolution over time, the architecture of transformers in LLMs, the different resources of LLMs, and the different training methods that have been used to train them. The paper also demonstrates the datasets utilized in the studies. After that, the paper discusses the wide range of applications of LLMs, including biomedical and healthcare, education, social, business, and agriculture. The study also illustrates how LLMs create an impact on society and shape the future of AI and how they can be used to solve real-world problems. Finally, the paper also explores open issues and challenges to deploy LLMs in real-world scenario. Our review paper aims to help practitioners, researchers, and experts thoroughly understand the evolution of LLMs, pre-trained architectures, applications, challenges, and future goals. Large Language Models (LLMs) recently demonstrated extraordinary capability, including natural language processing (NLP), language translation, text generation, question answering, etc. Moreover, LLMs are a new and essential part of computerized language processing, having the ability to understand complex verbal patterns and generate coherent and appropriate replies for the situation. Though this success of LLMs has prompted a substantial increase in research contributions, rapid growth has made it difficult to understand the overall impact of these improvements. Since a lot of new research on LLMs is coming out quickly, it is getting tough to get an overview of all of them in a short note. Consequently, the research community would benefit from a short but thorough review of the recent changes in this area. This article thoroughly overviews LLMs, including their history, architectures, transformers, resources, training methods, applications, impacts, challenges, etc. This paper begins by discussing the fundamental concepts of LLMs with its traditional pipeline of the LLMs training phase. It then provides an overview of the existing works, the history of LLMs, their evolution over time, the architecture of transformers in LLMs, the different resources of LLMs, and the different training methods that have been used to train them. It also demonstrated the datasets utilized in the studies. After that, the paper discusses the wide range of applications of LLMs, including biomedical and healthcare, education, social, business, and agriculture. It also illustrates how LLMs create an impact on society and shape the future of AI and how they can be used to solve real-world problems. Then it also explores open issues and challenges to deploying LLMs in real-world scenario. Our review paper aims to help practitioners, researchers, and experts thoroughly understand the evolution of LLMs, pre-trained architectures, applications, challenges, and future goals.
Author	Fahad, Nur Mohammad Ali, Mohammed Eunus Sakib, Sadman Azam, Sami Fatema, Kaniz Mim, Most. Marufatul Jannat Raiaan, Mohaimenul Azam Khan Ahmad, Jubaer Mukta, Md. Saddam Hossain
Author_xml	– sequence: 1 givenname: Mohaimenul Azam Khan orcidid: 0009-0006-4793-5382 surname: Raiaan fullname: Raiaan, Mohaimenul Azam Khan organization: Department of Computer Science and Engineering, United International University, Dhaka, Bangladesh – sequence: 2 givenname: Md. Saddam Hossain orcidid: 0000-0003-2675-5471 surname: Mukta fullname: Mukta, Md. Saddam Hossain organization: Department of Computer Science and Engineering, United International University, Dhaka, Bangladesh – sequence: 3 givenname: Kaniz surname: Fatema fullname: Fatema, Kaniz organization: Faculty of Science and Technology, Charles Darwin University, Australia – sequence: 4 givenname: Nur Mohammad surname: Fahad fullname: Fahad, Nur Mohammad organization: Department of Computer Science and Engineering, United International University, Dhaka, Bangladesh – sequence: 5 givenname: Sadman orcidid: 0009-0007-2007-5746 surname: Sakib fullname: Sakib, Sadman organization: Department of Computer Science and Engineering, United International University, Dhaka, Bangladesh – sequence: 6 givenname: Most. Marufatul Jannat orcidid: 0009-0000-7138-2331 surname: Mim fullname: Mim, Most. Marufatul Jannat organization: Department of Computer Science and Engineering, United International University, Dhaka, Bangladesh – sequence: 7 givenname: Jubaer surname: Ahmad fullname: Ahmad, Jubaer organization: Department of Computer Science and Engineering, United International University, Dhaka, Bangladesh – sequence: 8 givenname: Mohammed Eunus orcidid: 0000-0002-0384-7616 surname: Ali fullname: Ali, Mohammed Eunus organization: Department of CSE, Bangladesh University of Engineering and Technology (BUET), Dhaka, Bangladesh – sequence: 9 givenname: Sami orcidid: 0000-0001-7572-9750 surname: Azam fullname: Azam, Sami organization: Faculty of Science and Technology, Charles Darwin University, Australia
BookMark	eNp9UU1v1DAQtVCRKKW_AA6RuLKLvx1zi6IWVlpUqR9ny0nGW69SO9hZKP8eb1OkigNzsMfjeU9v5r1FJyEGQOg9wWtCsP7ctO3Fzc2aYsrXjEmhOH2FTimResUEkycv8jfoPOc9LlGXklCnyDXVNfz08KuKodratINyht3BluR7HGDMX6om9fd-hn4-JMifqmaaRt_b2cdQXrf2MYb44I8_VxOEapPzAXJlw1C193YcIewgv0OvnR0znD_fZ-ju8uK2_bbaXn3dtM121XOs55WwnJMBU4Kp0KCo0lR2jioiHVE1obwTJWpHnQMgTijaDXXnpOwsCEIIO0ObhXeIdm-m5B9s-m2i9eapENPO2DT7fgTDeG1xLx0wjDmVWkONheC6E3WnOqEK18eFa0rxRxlpNvt4SKHIN1QzXNZXBJUuvXT1KeacwJnez0_LmZP1oyHYHF0yi0vm6JJ5dqlg2T_Yv4r_j_qwoDwAvEBwVkbC7A9snZ2d
CODEN	IAECCG
CitedBy_id	crossref_primary_10_1109_ACCESS_2024_3513550 crossref_primary_10_35784_acs_6936 crossref_primary_10_1016_j_cosrev_2025_100762 crossref_primary_10_1109_ACCESS_2025_3538599 crossref_primary_10_3390_educsci14080814 crossref_primary_10_1007_s11004_025_10231_3 crossref_primary_10_1109_TIE_2024_3454408 crossref_primary_10_1109_ACCESS_2024_3445413 crossref_primary_10_1016_j_solener_2025_113927 crossref_primary_10_1007_s40593_025_00492_8 crossref_primary_10_1016_j_neucom_2024_128263 crossref_primary_10_3390_app15158570 crossref_primary_10_1109_ACCESS_2025_3600146 crossref_primary_10_3390_computers14030106 crossref_primary_10_1136_rapm_2025_106850 crossref_primary_10_1177_10497323251365211 crossref_primary_10_1080_10511253_2025_2506435 crossref_primary_10_1021_acssynbio_5c00391 crossref_primary_10_3390_buildings15071144 crossref_primary_10_1080_17425255_2025_2551724 crossref_primary_10_1097_CM9_0000000000003456 crossref_primary_10_1109_ACCESS_2025_3565280 crossref_primary_10_1109_ACCESS_2025_3529741 crossref_primary_10_1109_OJCS_2025_3580498 crossref_primary_10_1177_02683962251371062 crossref_primary_10_1002_eng2_70365 crossref_primary_10_1109_ACCESS_2025_3535782 crossref_primary_10_3390_vehicles7010011 crossref_primary_10_1109_ACCESS_2025_3532397 crossref_primary_10_1016_j_jnca_2024_103989 crossref_primary_10_1016_j_ipm_2025_104082 crossref_primary_10_3390_computers14070265 crossref_primary_10_1007_s00521_025_11618_3 crossref_primary_10_1007_s10586_024_04983_6 crossref_primary_10_1088_3049_4761_addac6 crossref_primary_10_1109_OJCOMS_2024_3522103 crossref_primary_10_1177_10732748241286749 crossref_primary_10_1371_journal_pone_0332134 crossref_primary_10_1016_j_tourman_2025_105271 crossref_primary_10_3390_app15126525 crossref_primary_10_7256_2454_0714_2025_2_74270 crossref_primary_10_1080_20964471_2025_2480446 crossref_primary_10_18203_2320_6012_ijrms20252009 crossref_primary_10_3390_computers14050162 crossref_primary_10_1007_s10664_025_10692_4 crossref_primary_10_1016_j_trip_2025_101599 crossref_primary_10_3390_eng5030068 crossref_primary_10_1080_10511253_2024_2413995 crossref_primary_10_1007_s10489_025_06256_0 crossref_primary_10_1109_ACCESS_2025_3568695 crossref_primary_10_1109_ACCESS_2025_3559135 crossref_primary_10_3390_electronics14091728 crossref_primary_10_1038_s41597_025_04417_x crossref_primary_10_3390_su17146379 crossref_primary_10_1177_21582440251368594 crossref_primary_10_3390_s25072024 crossref_primary_10_1109_ACCESS_2025_3596791 crossref_primary_10_3389_fpls_2025_1583344 crossref_primary_10_1109_ACCESS_2025_3582037 crossref_primary_10_3390_ijgi13100348 crossref_primary_10_1145_3718096 crossref_primary_10_3390_app142110048 crossref_primary_10_3390_ai6080188 crossref_primary_10_4018_JOEUC_383053 crossref_primary_10_1016_j_eswa_2025_127864 crossref_primary_10_3390_ai6050096 crossref_primary_10_1016_j_aei_2025_103142 crossref_primary_10_1016_j_aei_2025_103265 crossref_primary_10_3390_buildings15111944 crossref_primary_10_1007_s42979_024_03055_1 crossref_primary_10_1016_j_ijmedinf_2025_105787 crossref_primary_10_1109_ACCESS_2024_3464242 crossref_primary_10_3390_a17120582 crossref_primary_10_3390_smartcities7050107 crossref_primary_10_1515_zwf_2024_1175 crossref_primary_10_2478_jaiscr_2025_0007 crossref_primary_10_1016_j_jbi_2025_104778 crossref_primary_10_1109_ACCESS_2024_3468996 crossref_primary_10_1016_j_bdr_2025_100551 crossref_primary_10_3390_jcm13195909 crossref_primary_10_1061_JMENEA_MEENG_6705 crossref_primary_10_1007_s40558_024_00309_9 crossref_primary_10_1038_s41598_025_03298_9 crossref_primary_10_1016_j_advmem_2025_100161 crossref_primary_10_3390_electronics14091813 crossref_primary_10_1109_ACCESS_2025_3525849 crossref_primary_10_1007_s40688_025_00554_7 crossref_primary_10_1111_exsy_13760 crossref_primary_10_3390_resources13090119 crossref_primary_10_3390_su17031321 crossref_primary_10_1016_j_ipm_2025_104392 crossref_primary_10_3390_en18174701 crossref_primary_10_1007_s11517_025_03414_x crossref_primary_10_1093_jamia_ocaf008 crossref_primary_10_1016_j_chb_2025_108730 crossref_primary_10_1111_edt_13041 crossref_primary_10_1111_exsy_70051 crossref_primary_10_3390_designs8030043 crossref_primary_10_3390_electronics14010120 crossref_primary_10_3390_vehicles6030074 crossref_primary_10_1007_s44163_025_00339_0 crossref_primary_10_1038_s44401_025_00027_2 crossref_primary_10_3389_frai_2025_1545851 crossref_primary_10_1007_s11042_024_18608_y crossref_primary_10_1111_itor_70054 crossref_primary_10_1093_jamia_ocae202 crossref_primary_10_1109_ACCESS_2024_3410035 crossref_primary_10_3390_make7010003 crossref_primary_10_1080_17452007_2025_2456768 crossref_primary_10_1038_s41597_025_05268_2 crossref_primary_10_2196_71916 crossref_primary_10_1109_ACCESS_2025_3559204 crossref_primary_10_1016_j_paerosci_2025_101100 crossref_primary_10_1038_s44407_025_00027_4 crossref_primary_10_1186_s13326_025_00331_8 crossref_primary_10_1007_s10792_025_03711_2 crossref_primary_10_1097_ICL_0000000000001158 crossref_primary_10_1109_ACCESS_2025_3591966 crossref_primary_10_3390_info16050366 crossref_primary_10_1016_j_sftr_2025_101033 crossref_primary_10_1093_polsoc_puaf001 crossref_primary_10_3390_app15137134 crossref_primary_10_1016_j_autcon_2024_105846 crossref_primary_10_1109_ACCESS_2024_3428700 crossref_primary_10_1080_13683500_2024_2417712 crossref_primary_10_3390_app14125068 crossref_primary_10_1007_s41060_025_00744_9 crossref_primary_10_3390_informatics12030083 crossref_primary_10_1016_j_csi_2024_103951 crossref_primary_10_3390_ai6090216 crossref_primary_10_1016_j_knosys_2025_113151 crossref_primary_10_1016_j_knosys_2025_114361 crossref_primary_10_3390_app142411897 crossref_primary_10_1177_17562848251328577 crossref_primary_10_3390_electronics13245040 crossref_primary_10_1093_cid_ciae442 crossref_primary_10_1109_ACCESS_2024_3519264 crossref_primary_10_1007_s10660_025_09990_2 crossref_primary_10_3390_info16080688 crossref_primary_10_1007_s41060_025_00805_z crossref_primary_10_1016_j_foodcont_2024_111071 crossref_primary_10_2147_IJGM_S497753 crossref_primary_10_3390_app15147730 crossref_primary_10_1007_s10791_025_09580_8 crossref_primary_10_3389_frai_2025_1546179 crossref_primary_10_1109_ACCESS_2025_3527025 crossref_primary_10_1021_acsomega_5c04542 crossref_primary_10_3390_computers13110292 crossref_primary_10_1016_j_ymssp_2025_113226 crossref_primary_10_1007_s11613_025_00946_x crossref_primary_10_1093_icc_dtae042 crossref_primary_10_1016_j_bsheal_2025_09_007 crossref_primary_10_7717_peerj_cs_2293 crossref_primary_10_1007_s10639_024_13145_5 crossref_primary_10_1016_j_apenergy_2025_126382 crossref_primary_10_1016_j_joms_2025_03_015 crossref_primary_10_1109_ACCESS_2025_3542417 crossref_primary_10_1016_j_biocon_2025_111511 crossref_primary_10_1002_hcs2_70031 crossref_primary_10_1016_j_compag_2025_110442 crossref_primary_10_1109_MPRV_2025_3539421 crossref_primary_10_1016_j_eswa_2025_129753 crossref_primary_10_1177_14604582241304679 crossref_primary_10_1080_01691864_2025_2490601 crossref_primary_10_1016_j_jvcir_2024_104320 crossref_primary_10_3390_fi17060235 crossref_primary_10_1177_1088467X251348350 crossref_primary_10_1007_s11227_024_06413_1 crossref_primary_10_1108_JSM_11_2023_0441 crossref_primary_10_1109_ACCESS_2024_3426279 crossref_primary_10_1111_exsy_70127 crossref_primary_10_1007_s13735_024_00334_8 crossref_primary_10_1109_TIFS_2025_3602233 crossref_primary_10_3390_s25133987 crossref_primary_10_3390_app14146280 crossref_primary_10_1109_ACCESS_2024_3418900 crossref_primary_10_1145_3731680 crossref_primary_10_1007_s10462_025_11189_8 crossref_primary_10_1016_j_rcim_2025_102982 crossref_primary_10_1016_j_coms_2025_04_007 crossref_primary_10_3390_electronics14071384 crossref_primary_10_1109_ACCESS_2025_3555753 crossref_primary_10_1038_s42256_025_01005_x crossref_primary_10_23962_ajic_i35_21309 crossref_primary_10_3389_frai_2025_1638227 crossref_primary_10_1109_ACCESS_2024_3521945 crossref_primary_10_1016_j_compmedimag_2025_102581 crossref_primary_10_59294_HIUJS2025056 crossref_primary_10_3390_make7030097 crossref_primary_10_3390_batteries11030107 crossref_primary_10_3390_info16090792 crossref_primary_10_3390_computers14030093 crossref_primary_10_3390_network5030039 crossref_primary_10_1109_ACCESS_2025_3608650 crossref_primary_10_3390_app15148103 crossref_primary_10_1016_j_knosys_2025_113503 crossref_primary_10_1109_ACCESS_2025_3573955 crossref_primary_10_1016_j_knosys_2025_114391 crossref_primary_10_1016_j_landurbplan_2025_105323 crossref_primary_10_1016_j_osnem_2025_100311 crossref_primary_10_1108_ICS_03_2025_0093 crossref_primary_10_3390_electronics13153034
Cites_doi	10.18653/v1/P19-1356 10.18653/v1/2022.emnlp-main.42 10.21437/interspeech.2020-1511 10.1109/CONIT51480.2021.9498485 10.1007/978-3-030-90055-7_21 10.48550/ARXIV.1706.03762 10.1609/aaai.v36i10.21319 10.1007/s42452-019-1765-9 10.1016/j.ijinfomgt.2023.102642 10.1155/2023/8691095 10.18653/v1/2023.wmt-1.96 10.1038/s41591-023-02448-8 10.3390/a15020071 10.1016/j.csl.2014.11.004 10.1007/s00146-022-01494-z 10.18653/v1/2023.emnlp-main.4 10.1109/ICCECE51049.2023.10085092 10.1609/aaai.v36i10.21307 10.18653/v1/2020.emnlp-main.437 10.3390/bdcc7030124 10.1145/3503488 10.1016/j.iotcps.2023.04.003 10.18653/v1/2020.acl-main.362 10.18653/v1/2020.emnlp-demos.6 10.1016/j.simpat.2023.102754 10.2139/ssrn.4389233 10.5555/3104322.3104425 10.3390/logistics7020026 10.18653/v1/P18-1007 10.1016/j.psychres.2023.115334 10.1038/s41523-023-00557-8 10.1109/ISBI48211.2021.9434063 10.1007/s11023-020-09548-1 10.1145/3560815 10.3390/healthcare11060887 10.3115/992424.992434 10.1038/s41368-023-00239-y 10.1038/s41433-023-02759-7 10.2139/ssrn.4405389 10.33682/1dze-8739 10.1609/aaai.v35i15.17625 10.1145/3641289 10.1016/0893-6080(89)90020-8 10.18653/v1/2021.emnlp-main.243 10.1002/pra2.927 10.1109/ICASSP.2012.6289079 10.1016/j.mlwa.2023.100508 10.1007/978-3-030-37591-1_6 10.1002/j.1538-7305.1988.tb00232.x 10.3389/fpubh.2023.1166120 10.1126/science.298.5598.1569 10.1007/s12652-021-03439-8 10.1007/s10514-023-10132-6 10.1038/s41746-021-00464-x 10.1126/science.abq1158 10.2139/ssrn.4405391 10.1007/978-1-4842-8844-3_4 10.1515/9783110867275.105 10.1093/bib/bbac409 10.1109/ICCCI48352.2020.9104105 10.1093/mind/LIX.236.433 10.18653/v1/2020.findings-emnlp.151 10.3390/fi15120372 10.18653/v1/2023.emnlp-main.96 10.1148/radiol.230163 10.1007/s10489-022-03865-x 10.1109/ACCESS.2023.3272228 10.18653/v1/2023.acl-long.893 10.18653/v1/2022.findings-acl.146 10.1038/d41586-023-00816-5 10.48550/ARXIV.1907.11692 10.1021/acs.est.3c01106 10.1109/ECCE57851.2023.10101527 10.1007/s11127-023-01097-2 10.1177/20539517211047734 10.1109/SLT48900.2021.9383557 10.18653/v1/2022.bigscience-1.9 10.1016/j.techfore.2022.121559 10.3390/biomedicines11061566 10.3390/jsan12040061 10.1145/3458754 10.1007/s11023-022-09602-0 10.1111/1748-8583.12524 10.1371/journal.pdig.0000198 10.1109/TASLP.2021.3082299 10.1093/bioinformatics/btz682 10.1016/j.ijsu.2021.105906 10.1016/j.chb.2022.107540 10.1108/LHTN-01-2023-0009 10.18653/v1/W19-4808 10.1609/aaai.v35i17.17744 10.18653/v1/P19-1493 10.1007/978-3-030-72188-6_2 10.4324/9781315558325-4 10.1007/s10916-023-01925-4 10.21437/Interspeech.2010-343 10.18653/v1/2020.acl-demos.30 10.1016/j.lindif.2023.102274 10.1109/ASRU51503.2021.9688232 10.1007/s40558-023-00248-x 10.18653/v1/2023.findings-acl.67 10.3390/educsci13040410 10.1016/B978-0-12-819314-3.00005-7
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024
DBID	97E ESBDL RIA RIE AAYXX CITATION 7SC 7SP 7SR 7T9 8BQ 8FD JG9 JQ2 L7M L~C L~D DOA
DOI	10.1109/ACCESS.2024.3365742
DatabaseName	IEEE Xplore (IEEE) IEEE Xplore Open Access Journals IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Engineered Materials Abstracts Linguistics and Language Behavior Abstracts (LLBA) METADEX Technology Research Database Materials Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional DOAJ Directory of Open Access Journals
DatabaseTitle	CrossRef Materials Research Database Engineered Materials Abstracts Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Linguistics and Language Behavior Abstracts (LLBA) Advanced Technologies Database with Aerospace METADEX Computer and Information Systems Abstracts Professional
DatabaseTitleList	Materials Research Database
Database_xml	– sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering Agriculture
EISSN	2169-3536
EndPage	1
ExternalDocumentID	oai_doaj_org_article_348a0c6fe30042699e805549b58b7b57 10_1109_ACCESS_2024_3365742 10433480
Genre	orig-research
GrantInformation_xml	– fundername: Institute of Advance Research, United International University
GroupedDBID	0R~ 5VS 6IK 97E AAJGR ABAZT ABVLG ACGFS ADBBV ALMA_UNASSIGNED_HOLDINGS BCNDV BEFXN BFFAM BGNUA BKEBE BPEOZ EBS ESBDL GROUPED_DOAJ IPLJI JAVBF KQ8 M43 M~E O9- OCL OK1 RIA RIE RNS 4.4 AAYXX AGSQL CITATION EJD 7SC 7SP 7SR 7T9 8BQ 8FD JG9 JQ2 L7M L~C L~D
ID	FETCH-LOGICAL-c409t-5a441d0210259e727926bf2716f178124b55558f2ffee1f572bd8bf66bae51113
IEDL.DBID	RIE
ISICitedReferencesCount	278
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001173153100001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	2169-3536
IngestDate	Fri Oct 03 12:52:41 EDT 2025 Sat Nov 08 00:13:32 EST 2025 Sat Nov 29 06:25:29 EST 2025 Tue Nov 18 22:15:14 EST 2025 Wed Aug 27 02:17:14 EDT 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Language	English
License	https://creativecommons.org/licenses/by-nc-nd/4.0
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c409t-5a441d0210259e727926bf2716f178124b55558f2ffee1f572bd8bf66bae51113
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0009-0000-7138-2331 0009-0007-2007-5746 0009-0006-4793-5382 0000-0001-7572-9750 0000-0002-0384-7616 0000-0003-2675-5471 0000-0002-0787-5403
OpenAccessLink	https://ieeexplore.ieee.org/document/10433480
PQID	2930957124
PQPubID	4845423
PageCount	1
ParticipantIDs	crossref_citationtrail_10_1109_ACCESS_2024_3365742 crossref_primary_10_1109_ACCESS_2024_3365742 proquest_journals_2930957124 doaj_primary_oai_doaj_org_article_348a0c6fe30042699e805549b58b7b57 ieee_primary_10433480
PublicationCentury	2000
PublicationDate	2024-01-01
PublicationDateYYYYMMDD	2024-01-01
PublicationDate_xml	– month: 01 year: 2024 text: 2024-01-01 day: 01
PublicationDecade	2020
PublicationPlace	Piscataway
PublicationPlace_xml	– name: Piscataway
PublicationTitle	IEEE access
PublicationTitleAbbrev	Access
PublicationYear	2024
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	Onat Topal (ref34) 2021 ref56 Hoffmann (ref78) 2022 ref59 ref52 Lisa Li (ref57) 2021 ref169 Radford (ref39) 2024 Jain (ref177) 2023 Azunre (ref28) 2021 Jiang (ref183) 2023 ref170 Thi Nguyen (ref76) 2023 Sanh (ref151) 2019 ref51 Huang (ref142) 2019 ref175 Xue (ref179) 2020 Weingart (ref168) ref176 Smith (ref74) 2022 ref171 ref172 ref46 (ref115) 2023 ref45 Shazeer (ref99) 2020 ref47 ref42 Naveed (ref82) 2023 Iqbal (ref187) 2023 ref44 Wei (ref80); 35 Ramabhadran (ref7) Yu (ref134) 2023 Juang (ref25) 2005; 1 ref49 ref8 ref181 ref9 ref4 ref6 ref5 ref101 Rae (ref72) 2021 ref182 Peng (ref146) 2023 ref35 Awasthi (ref160) 2022 Wu (ref31) 2016 ref37 ref36 ref148 ref30 (ref114) 2023 ref149 ref33 ref32 ref147 Chowdhery (ref69) 2022 ref38 Shoeybi (ref43) 2019 Kraljevic (ref132) 2022 Taori (ref15) 2023 ref156 Saba (ref184) 2023 ref154 Sennrich (ref48) 2015 Penedo (ref77) 2023 Sun (ref173) 2023 Lan (ref152) 2019 ref24 Gat (ref157) 2023 ref23 ref26 ref159 ref22 ref158 Ratner (ref180) 2022 ref27 ref29 Du (ref100) Meng (ref174) Fan (ref16) 2023 ref166 ref164 ref165 ref162 ref163 ref13 ref12 Hendrycks (ref53) 2016 ref128 Conneau (ref150) 2019 Li (ref167) 2023 ref129 Liu (ref186) 2023 ref97 ref126 ref96 ref127 ref11 ref124 (ref116) 2023 ref125 ref17 ref19 ref18 Lu (ref64); 34 Peng (ref95) 2023 ref133 ref92 ref131 ref94 Pinker (ref1) 2003 Sridhar (ref161) 2023 ref130 ref91 ref90 ref89 Shen (ref93) 2023 ref139 ref85 ref138 Hadi (ref20) 2023 Touvron (ref75) 2023 ref88 ref135 Thoppilan (ref70) 2022 ref136 (ref113) 2023 Zeng (ref81) 2021 Chung (ref58) 2022 Hadi (ref137) 2023 ref144 ref145 ref84 ref83 ref143 Zhang (ref185) 2023 ref141 ref108 ref109 ref106 ref104 ref2 Dao (ref105) 2023 Brown (ref155) Zhu (ref178) 2023 Yang (ref107); 32 Zhao (ref3) 2023 Devlin (ref10) 2018 Pichai (ref14) 2023 Lieber (ref73) 2021; 1 ref111 Bolukbasi (ref153); 29 Fan (ref87) 2023 Hagendorff (ref103) 2022 ref112 Wang (ref121) 2023 Nijkamp (ref102) 2022 ref110 Koizumi (ref86) 2020 Radford (ref41) 2019; 1 ref68 ref119 ref67 ref118 Workshop (ref55) ref63 ref66 Chen (ref122) 2023 Zong (ref140) 2022 ref65 Ghojogh (ref40) 2024 Cronin (ref21) 2004; 39 Child (ref50) 2019 Zhang (ref54); 32 Taylor (ref98) 2022 (ref117) 2023 Zeng (ref71) 2022 Zhang (ref79) 2022 ref60 ref123 ref62 ref120 ref61
References_xml	– year: 2023 ident: ref146 article-title: Embedding-based retrieval with LLM for effective agriculture information extracting from unstructured data publication-title: arXiv:2308.03107 – ident: ref83 doi: 10.18653/v1/P19-1356 – year: 2023 ident: ref95 article-title: Instruction tuning with GPT-4 publication-title: arXiv:2304.03277 – year: 2020 ident: ref99 article-title: GLU variants improve transformer publication-title: arXiv:2002.05202 – year: 2022 ident: ref103 article-title: Thinking fast and slow in large language models publication-title: arXiv:2212.05206 – ident: ref112 doi: 10.18653/v1/2022.emnlp-main.42 – volume: 32 volume-title: Proc. Adv. Neural Inf. Process. Syst. ident: ref54 article-title: Root mean square layer normalization – ident: ref108 doi: 10.21437/interspeech.2020-1511 – year: 2023 ident: ref161 article-title: Harnessing LLMs in curricular design: Using GPT-4 to support authoring of learning objectives publication-title: arXiv:2306.17459 – year: 2019 ident: ref152 article-title: ALBERT: A lite BERT for self-supervised learning of language representations publication-title: arXiv:1909.11942 – volume-title: IBM Watson Natural Language Understanding year: 2023 ident: ref117 – ident: ref32 doi: 10.1109/CONIT51480.2021.9498485 – ident: ref30 doi: 10.1007/978-3-030-90055-7_21 – year: 2022 ident: ref58 article-title: Scaling instruction-finetuned language models publication-title: arXiv:2210.11416 – ident: ref9 doi: 10.48550/ARXIV.1706.03762 – ident: ref63 doi: 10.1609/aaai.v36i10.21319 – year: 2021 ident: ref81 article-title: PanGu-α: Large-scale autoregressive pretrained Chinese language models with auto-parallel computation publication-title: arXiv:2104.12369 – ident: ref36 doi: 10.1007/s42452-019-1765-9 – ident: ref139 doi: 10.1016/j.ijinfomgt.2023.102642 – year: 2021 ident: ref57 article-title: Prefix-tuning: Optimizing continuous prompts for generation publication-title: arXiv:2101.00190 – ident: ref172 doi: 10.1155/2023/8691095 – ident: ref111 doi: 10.18653/v1/2023.wmt-1.96 – ident: ref125 doi: 10.1038/s41591-023-02448-8 – year: 2018 ident: ref10 article-title: BERT: Pre-training of deep bidirectional transformers for language understanding publication-title: arXiv:1810.04805 – volume-title: A taxonomy for deriving business insights from user-generated content ident: ref168 – ident: ref94 doi: 10.3390/a15020071 – ident: ref29 doi: 10.1016/j.csl.2014.11.004 – year: 2022 ident: ref98 article-title: Galactica: A large language model for science publication-title: arXiv:2211.09085 – year: 2023 ident: ref20 article-title: A survey on large language models: Applications, challenges, limitations, and practical usage publication-title: TechRxiv – ident: ref27 doi: 10.1007/s00146-022-01494-z – year: 2022 ident: ref102 article-title: CodeGen: An open large language model for code with multi-turn program synthesis publication-title: arXiv:2203.13474 – ident: ref89 doi: 10.18653/v1/2023.emnlp-main.4 – year: 2023 ident: ref185 article-title: Multimodal chain-of-thought reasoning in language models publication-title: arXiv:2302.00923 – volume-title: Attention Mechanism, Transformers, BERT, and GPT: Tutorial and Survey year: 2024 ident: ref40 – ident: ref162 doi: 10.1109/ICCECE51049.2023.10085092 – ident: ref175 doi: 10.1609/aaai.v36i10.21307 – year: 2023 ident: ref122 article-title: Evaluation of ChatGPT family of models for biomedical reasoning and classification publication-title: arXiv:2304.02496 – year: 2023 ident: ref93 article-title: Large language models empowered autonomous edge AI for connected intelligence publication-title: arXiv:2307.02779 – start-page: 24457 volume-title: Proc. Int. Conf. Mach. Learn. ident: ref174 article-title: Tuning language models as training data generators for augmentation-enhanced few-shot learning – ident: ref68 doi: 10.18653/v1/2020.emnlp-main.437 – volume: 35 start-page: 24824 volume-title: Proc. Adv. Neural Inf. Process. Syst. ident: ref80 article-title: Chain-of-thought prompting elicits reasoning in large language models – ident: ref42 doi: 10.3390/bdcc7030124 – ident: ref182 doi: 10.1145/3503488 – ident: ref104 doi: 10.1016/j.iotcps.2023.04.003 – ident: ref143 doi: 10.18653/v1/2020.acl-main.362 – year: 2020 ident: ref86 article-title: Audio captioning using pre-trained large-scale language model guided by audio-based similar caption retrieval publication-title: arXiv:2012.07331 – ident: ref35 doi: 10.18653/v1/2020.emnlp-demos.6 – ident: ref119 doi: 10.1016/j.simpat.2023.102754 – year: 2023 ident: ref157 article-title: Faithful explanations of black-box NLP models using LLM-generated counterfactuals publication-title: arXiv:2310.00603 – ident: ref44 doi: 10.2139/ssrn.4389233 – year: 2023 ident: ref134 article-title: Temporal data meets LLM—Explainable financial time series forecasting publication-title: arXiv:2306.11025 – ident: ref52 doi: 10.5555/3104322.3104425 – ident: ref135 doi: 10.3390/logistics7020026 – ident: ref47 doi: 10.18653/v1/P18-1007 – ident: ref97 doi: 10.1016/j.psychres.2023.115334 – volume: 1 start-page: 9 year: 2021 ident: ref73 article-title: Jurassic-1: Technical details and evaluation publication-title: White Paper. AI21 Labs – ident: ref124 doi: 10.1038/s41523-023-00557-8 – start-page: 1 volume-title: Proc. NAACL-HLT ident: ref7 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 – year: 2022 ident: ref74 article-title: Using DeepSpeed and megatron to train megatron-turing NLG 530B, a large-scale generative language model publication-title: arXiv:2201.11990 – ident: ref11 doi: 10.1109/ISBI48211.2021.9434063 – ident: ref65 doi: 10.1007/s11023-020-09548-1 – ident: ref60 doi: 10.1145/3560815 – year: 2021 ident: ref72 article-title: Scaling language models: Methods, analysis & insights from training gopher publication-title: arXiv:2112.11446 – year: 2023 ident: ref121 article-title: On the robustness of ChatGPT: An adversarial and out-of-distribution perspective publication-title: arXiv:2302.12095 – ident: ref128 doi: 10.3390/healthcare11060887 – volume-title: An Important Next Step on Our AI Journey year: 2023 ident: ref14 – ident: ref46 doi: 10.3115/992424.992434 – ident: ref123 doi: 10.1038/s41368-023-00239-y – ident: ref163 doi: 10.1038/s41433-023-02759-7 – year: 2023 ident: ref77 article-title: The RefinedWeb dataset for falcon LLM: Outperforming curated corpora with web data, and web data only publication-title: arXiv:2306.01116 – ident: ref145 doi: 10.2139/ssrn.4405389 – ident: ref90 doi: 10.33682/1dze-8739 – ident: ref109 doi: 10.1609/aaai.v35i15.17625 – ident: ref17 doi: 10.1145/3641289 – ident: ref51 doi: 10.1016/0893-6080(89)90020-8 – year: 2022 ident: ref69 article-title: PaLM: Scaling language modeling with pathways publication-title: arXiv:2204.02311 – ident: ref56 doi: 10.18653/v1/2021.emnlp-main.243 – year: 2021 ident: ref34 article-title: Exploring transformers in natural language generation: GPT, BERT, and XLNet publication-title: arXiv:2102.08036 – ident: ref106 doi: 10.1002/pra2.927 – ident: ref49 doi: 10.1109/ICASSP.2012.6289079 – ident: ref166 doi: 10.1016/j.mlwa.2023.100508 – ident: ref22 doi: 10.1007/978-3-030-37591-1_6 – year: 2022 ident: ref79 article-title: OPT: Open pre-trained transformer language models publication-title: arXiv:2205.01068 – year: 2023 ident: ref137 article-title: Large language models: A comprehensive survey of its applications, challenges, limitations, and future prospects – volume: 29 volume-title: Proc. Adv. Neural Inf. Process. Syst. ident: ref153 article-title: Man is to computer programmer as woman is to homemaker? Debiasing word embeddings – ident: ref24 doi: 10.1002/j.1538-7305.1988.tb00232.x – ident: ref127 doi: 10.3389/fpubh.2023.1166120 – ident: ref2 doi: 10.1126/science.298.5598.1569 – year: 2023 ident: ref16 article-title: A bibliometric review of large language models research from 2017 to 2023 publication-title: arXiv:2304.02020 – year: 2019 ident: ref50 article-title: Generating long sequences with sparse transformers publication-title: arXiv:1904.10509 – ident: ref37 doi: 10.1007/s12652-021-03439-8 – year: 2023 ident: ref105 article-title: Performance comparison of large language models on VNHSGE English dataset: OpenAI chatGPT, Microsoft bing chat, and Google bard publication-title: arXiv:2307.02288 – year: 2023 ident: ref82 article-title: A comprehensive overview of large language models publication-title: arXiv:2307.06435 – ident: ref92 doi: 10.1007/s10514-023-10132-6 – ident: ref126 doi: 10.1038/s41746-021-00464-x – year: 2023 ident: ref167 article-title: EcomGPT: Instruction-tuning large language models with chain-of-task tasks for e-commerce publication-title: arXiv:2308.06966 – ident: ref85 doi: 10.1126/science.abq1158 – volume: 32 volume-title: Proc. Adv. Neural Inf. Process. Syst. ident: ref107 article-title: XLNet: Generalized autoregressive pretraining for language understanding – ident: ref147 doi: 10.2139/ssrn.4405391 – year: 2023 ident: ref177 article-title: Bring your own data! Self-supervised evaluation for large language models publication-title: arXiv:2306.13651 – start-page: 5547 volume-title: Proc. Int. Conf. Mach. Learn. ident: ref100 article-title: GLaM: Efficient scaling of language models with mixture-of-experts – ident: ref120 doi: 10.1007/978-1-4842-8844-3_4 – ident: ref23 doi: 10.1515/9783110867275.105 – ident: ref110 doi: 10.1093/bib/bbac409 – ident: ref118 doi: 10.1109/ICCCI48352.2020.9104105 – year: 2023 ident: ref76 article-title: Fine-tuning llama 2 large language models for detecting online sexual predatory chats and abusive texts publication-title: arXiv:2308.14683 – year: 2020 ident: ref179 article-title: MT5: A massively multilingual pre-trained text-to-text transformer publication-title: arXiv:2010.11934 – ident: ref4 doi: 10.1093/mind/LIX.236.433 – ident: ref144 doi: 10.18653/v1/2020.findings-emnlp.151 – year: 2023 ident: ref184 article-title: Towards explainable and language-agnostic LLMs: Symbolic reverse engineering of language at scale publication-title: arXiv:2306.00017 – year: 2016 ident: ref31 article-title: Google’s neural machine translation system: Bridging the gap between human and machine translation publication-title: arXiv:1609.08144 – ident: ref148 doi: 10.3390/fi15120372 – year: 2022 ident: ref140 article-title: A survey on GPT-3 publication-title: arXiv:2212.00857 – year: 2023 ident: ref75 article-title: LLaMA: Open and efficient foundation language models publication-title: arXiv:2302.13971 – year: 2023 ident: ref173 article-title: A short survey of viewing large language models in legal aspect publication-title: arXiv:2303.09136 – year: 2019 ident: ref150 article-title: Unsupervised cross-lingual representation learning at scale publication-title: arXiv:1911.02116 – ident: ref158 doi: 10.18653/v1/2023.emnlp-main.96 – ident: ref5 doi: 10.1148/radiol.230163 – ident: ref61 doi: 10.1007/s10489-022-03865-x – volume-title: Alpaca: A Strong, Replicable Instruction-following Model year: 2023 ident: ref15 – year: 2022 ident: ref70 article-title: LaMDA: Language models for dialog applications publication-title: arXiv:2201.08239 – year: 2023 ident: ref178 article-title: A survey on model compression for large language models publication-title: arXiv:2308.07633 – ident: ref6 doi: 10.1109/ACCESS.2023.3272228 – ident: ref62 doi: 10.18653/v1/2023.acl-long.893 – ident: ref84 doi: 10.18653/v1/2022.findings-acl.146 – ident: ref13 doi: 10.1038/d41586-023-00816-5 – ident: ref67 doi: 10.48550/ARXIV.1907.11692 – year: 2023 ident: ref87 article-title: Recommender systems in the era of large language models (LLMs) publication-title: arXiv:2307.02046 – year: 2019 ident: ref151 article-title: DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter publication-title: arXiv:1910.01108 – year: 2023 ident: ref186 article-title: Dynamic LLM-agent network: An LLM-agent collaboration framework with agent team optimization publication-title: arXiv:2310.02170 – ident: ref171 doi: 10.1021/acs.est.3c01106 – year: 2023 ident: ref187 article-title: LLM platform security: Applying a systematic evaluation framework to OpenAI’s ChatGPT plugins publication-title: arXiv:2309.10254 – ident: ref176 doi: 10.1109/ECCE57851.2023.10101527 – ident: ref181 doi: 10.1007/s11127-023-01097-2 – volume-title: arXiv:2211.05100 ident: ref55 article-title: BLOOM: A 176B-parameter open-access multilingual language model – volume: 39 volume-title: Annual review of information science and technology year: 2004 ident: ref21 – volume-title: Improving Language Understanding by Generative Pre-Training year: 2024 ident: ref39 – volume: 1 start-page: 9 issue: 8 year: 2019 ident: ref41 article-title: Language models are unsupervised multitask learners publication-title: OpenAI Blog – volume-title: The Language Instinct: How the Mind Creates Language year: 2003 ident: ref1 – ident: ref33 doi: 10.1177/20539517211047734 – volume-title: Transfer Learning for Natural Language Processing year: 2021 ident: ref28 – ident: ref91 doi: 10.1109/SLT48900.2021.9383557 – ident: ref101 doi: 10.18653/v1/2022.bigscience-1.9 – volume-title: Google Cloud year: 2023 ident: ref115 – ident: ref26 doi: 10.1016/j.techfore.2022.121559 – ident: ref59 doi: 10.3390/biomedicines11061566 – ident: ref159 doi: 10.3390/jsan12040061 – year: 2023 ident: ref183 article-title: Low-parameter federated learning with large language models publication-title: arXiv:2307.13896 – volume-title: OpenAI year: 2023 ident: ref113 – year: 2022 ident: ref71 article-title: GLM-130B: An open bilingual pre-trained model publication-title: arXiv:2210.02414 – year: 2019 ident: ref43 article-title: Megatron-LM: Training multi-billion parameter language models using model parallelism publication-title: arXiv:1909.08053 – volume-title: Huggingface year: 2023 ident: ref114 – ident: ref131 doi: 10.1145/3458754 – year: 2019 ident: ref142 article-title: Clinical XLNet: Modeling sequential clinical notes and predicting prolonged mechanical ventilation publication-title: arXiv:1912.11975 – ident: ref136 doi: 10.1007/s11023-022-09602-0 – ident: ref165 doi: 10.1111/1748-8583.12524 – ident: ref130 doi: 10.1371/journal.pdig.0000198 – ident: ref88 doi: 10.1109/TASLP.2021.3082299 – ident: ref156 doi: 10.1093/bioinformatics/btz682 – ident: ref45 doi: 10.1016/j.ijsu.2021.105906 – ident: ref170 doi: 10.1016/j.chb.2022.107540 – year: 2022 ident: ref180 article-title: Parallel context windows for large language models publication-title: arXiv:2212.10947 – ident: ref38 doi: 10.1108/LHTN-01-2023-0009 – ident: ref96 doi: 10.18653/v1/W19-4808 – ident: ref12 doi: 10.1609/aaai.v35i17.17744 – volume: 34 start-page: 21297 volume-title: Proc. Adv. Neural Inf. Process. Syst. ident: ref64 article-title: SOFT: Softmax-free transformer with linear complexity – start-page: 1877 volume-title: Proc. NIPS ident: ref155 article-title: Language models are few-shot learners – year: 2016 ident: ref53 article-title: Gaussian error linear units (GELUs) publication-title: arXiv:1606.08415 – ident: ref149 doi: 10.18653/v1/P19-1493 – year: 2022 ident: ref160 article-title: Bootstrapping multilingual semantic parsers using large language models publication-title: arXiv:2210.07313 – year: 2022 ident: ref78 article-title: Training compute-optimal large language models publication-title: arXiv:2203.15556 – ident: ref169 doi: 10.1007/978-3-030-72188-6_2 – year: 2023 ident: ref3 article-title: A survey of large language models publication-title: arXiv:2303.18223 – year: 2015 ident: ref48 article-title: Neural machine translation of rare words with subword units publication-title: arXiv:1508.07909 – ident: ref164 doi: 10.4324/9781315558325-4 – volume-title: Azure year: 2023 ident: ref116 – ident: ref129 doi: 10.1007/s10916-023-01925-4 – ident: ref8 doi: 10.21437/Interspeech.2010-343 – ident: ref154 doi: 10.18653/v1/2020.acl-demos.30 – ident: ref19 doi: 10.1016/j.lindif.2023.102274 – ident: ref66 doi: 10.1109/ASRU51503.2021.9688232 – ident: ref133 doi: 10.1007/s40558-023-00248-x – year: 2022 ident: ref132 article-title: Foresight-generative pretrained transformer (GPT) for modelling of patient timelines using EHRs publication-title: arXiv:2212.08072 – volume: 1 start-page: 67 year: 2005 ident: ref25 article-title: Automatic speech recognition—A brief history of the technology development – ident: ref18 doi: 10.18653/v1/2023.findings-acl.67 – ident: ref138 doi: 10.3390/educsci13040410 – ident: ref141 doi: 10.1016/B978-0-12-819314-3.00005-7
SSID	ssj0000816957
Score	2.6979144
Snippet	Large Language Models (LLMs) recently demonstrated extraordinary capability, including natural language processing (NLP), language translation, text... Large Language Models (LLMs) recently demonstrated extraordinary capability in various natural language processing (NLP) tasks including language translation,...
SourceID	doaj proquest crossref ieee
SourceType	Open Website Aggregation Database Enrichment Source Index Database Publisher
StartPage	1
SubjectTerms	Agriculture Application Artificial intelligence Automatic text generation Biomedicine Challenges Cognition Community research Computerization Evolution Health care Health services Information analysis Language Language modeling Language translation Large Language Models Large language models (LLM) Linguistics Natural language generation Natural language processing natural language processing (NLP) pre-trained models Pretrained models Question answering (information retrieval) Surveys Task analysis Taxonomy Training Transformer Transformers Translation World problems
SummonAdditionalLinks	– databaseName: DOAJ Directory of Open Access Journals dbid: DOA link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV07T8MwELYQYoAB8SiiUJAHxobm5ThmCxUVA6oYitTNshOfhFSlqCmIn4_PTqsgJFhYMiSOHN9dfHf2-fsIuckMaKFDE5QhQGCNQgQKIgh0qPK00hWwMnVkE3w6zedz8dyh-sKaMA8P7AU3StJchWUGJnHhvhAmD60LFJrlmmvmzpHbqKeTTLk5OI8ywXgLMxSFYlSMx3ZENiGM09skyRhP42-uyCH2txQrP-Zl52wmR-SwjRJp4b_umOyY-oQcdLADTwkU1K_r02VNn7Ce21792iNFgrNFc0eLzi5BM6RFZ7N6SGfq051JxidYVkI9ER9VdUXHG4qVpkdeJg-z8WPQkiYEpU3V1gFTNsCpXCbHhOGID5hpiG1aBBFHb64ZQnxBDGBMBIzHuso1ZJlWhiHv_BnZrZe1OSc0UoKDzrlOmBU9KCWQyipiWgCP4pL3SbyRnyxbRHEktlhIl1mEQnqhSxS6bIXeJ8PtS28eUOP35veomG1TRMN2N6yNyNZG5F820ic9VGunvxQPIId9MtjoWba_biNt_GPDTjvA9OI_-r4k-zgev2ozILvr1bu5Invlx_q1WV07q_0CPbbqyA priority: 102 providerName: Directory of Open Access Journals
Title	A Review on Large Language Models: Architectures, Applications, Taxonomies, Open Issues and Challenges
URI	https://ieeexplore.ieee.org/document/10433480 https://www.proquest.com/docview/2930957124 https://doaj.org/article/348a0c6fe30042699e805549b58b7b57
Volume	12
WOSCitedRecordID	wos001173153100001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 2169-3536 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000816957 issn: 2169-3536 databaseCode: DOA dateStart: 20130101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources (ISSN International Center) customDbUrl: eissn: 2169-3536 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000816957 issn: 2169-3536 databaseCode: M~E dateStart: 20130101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3NS-wwEA8-8eA7-PGe8tYvcvC41bbbNI23uigeVDwoeAtJmwFBug-7iif_dmeS7LIiCl5CaROa9JdpZiaZ-TF2WDqwyqYuaVKABCeFSgxkkNjUVEVrWxBN4ckm5PV1dX-vbmKwuo-Fcc75w2fuiC79Xn47aZ7JVYYSXlDgKFrov6SUIVhr7lAhBgklZMwslKXquB6PcRBoA-bF0WhUClnkH1Yfn6Q_sqp8-hX79eV8_Yc922BrUZHkdUB-ky257g_7vZBe8C-DmgfXP590_JKOfGMZ3JOcONAe-xNeL2wk9ENeL-xnD_mtefVhy_SETp7wwNXHTdfy8YyFpd9id-dnt-OLJPIqJA1ac9NEGNSBWm_sCeUkpRAsLeRoOUEmacG3grKAQQ7gXAZC5ratLJSlNU4QNf02W-4mnfvHeGaUBFtJOxIo_WCMIrarTFgFMssbOWD57HvrJiYdJ-6LR-2Nj1TpAJImkHQEacCG80b_Q86N76ufEpDzqpQw299AhHSUP43gmLQpwY281aiUq1LUpJQVlZVWYEe3CNWF9wVAB2xvNi90lO5eo4qEmikOsNj5otkuW6UuBl_NHluePj27fbbSvEwf-qcDb_hjefV2duAn8Tuhf-vR
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3Pa9swFBajG7Q7rOuPsazdqkOPcWs7lmX15oaVjqahhxR6E5KtB4XgjDod-_P3nqSElNHBLsbYMpb8SdZ7T3rfx9hp6cAqm7qkSQES7BQqMZBBYlNTFa1tQTSFF5uQ02n18KDuYrK6z4VxzvnNZ-6MTv1afrtonilUhiO8oMRR9NDfiqLIs5CutQ6pkIaEEjJyC2WpOq_HY2wGeoF5cTYalUIW-Yv5x9P0R12Vv37Gfoa52v3Pun1kH6IpyeuA_R5747p99n6DYPCAQc1D8J8vOj6hTd94DAFKTipo8_6C1xtLCf2Q1xsr2kM-M7994jLdob0nPKj1cdO1fLzSYekP2f3V99n4OonKCkmD_twyEQatoNa7e0I5SSSCpYUcfSfIJE35VhAPGOQAzmUgZG7bykJZWuMEidN_YlvdonOfGc-MkmAraUcCxz8Yo0jvKhNWgczyRg5Yvvreuom046R-Mdfe_UiVDiBpAklHkAZsuH7oZ2Dd-HfxSwJyXZQos_0FREjHEagRHJM2JbiR9xuVclWKtpSyorLSCqzoIaG68b4A6IAdr_qFjuO712gkoW2KDSy-vPLYCdu-nt1O9OTH9OaI7VB1Q-TmmG0tn57dV_au-bV87J---U78B-_K7PI
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=A+Review+on+Large+Language+Models%3A+Architectures%2C+Applications%2C+Taxonomies%2C+Open+Issues+and+Challenges&rft.jtitle=IEEE+access&rft.au=Raiaan%2C+Mohaimenul+Azam+Khan&rft.au=Mukta%2C+Md.+Saddam+Hossain&rft.au=Fatema%2C+Kaniz&rft.au=Fahad%2C+Nur+Mohammad&rft.date=2024-01-01&rft.pub=IEEE&rft.eissn=2169-3536&rft.spage=1&rft.epage=1&rft_id=info:doi/10.1109%2FACCESS.2024.3365742&rft.externalDocID=10433480
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2169-3536&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2169-3536&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2169-3536&client=summon