{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T04:55:19Z","timestamp":1790052919365,"version":"4.0.1"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T00:00:00Z","timestamp":1710288000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T00:00:00Z","timestamp":1710288000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Artif Intell Rev"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>This primer provides an overview of the rapidly evolving field of generative artificial intelligence, specifically focusing on large language models like ChatGPT (OpenAI) and Bard (Google). Large language models have demonstrated unprecedented capabilities in responding to natural language prompts. The aim of this primer is to demystify the underlying theory and architecture of large language models, providing intuitive explanations for a broader audience. Learners seeking to gain insight into the technical underpinnings of large language models must sift through rapidly growing and fragmented literature on the topic. This primer brings all the main concepts into a single digestible document. Topics covered include text tokenization, vocabulary construction, token embedding, context embedding with attention mechanisms, artificial neural networks, and objective functions in model training. The primer also explores state-of-the-art methods in training large language models to generalize on specific applications and to align with human intentions. Finally, an introduction to the concept of prompt engineering highlights the importance of effective human-machine interaction through natural language in harnessing the full potential of artificial intelligence chatbots. This comprehensive yet accessible primer will benefit students and researchers seeking foundational knowledge and a deeper understanding of the inner workings of existing and emerging artificial intelligence models. The author hopes that the primer will encourage further responsible innovation and informed discussions about these increasingly powerful tools.<\/jats:p>","DOI":"10.1007\/s10462-024-10720-7","type":"journal-article","created":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T02:09:39Z","timestamp":1710295779000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["Unraveling the mysteries of AI chatbots"],"prefix":"10.1007","volume":"57","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3743-6652","authenticated-orcid":false,"given":"Raj","family":"Bridgelall","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,3,13]]},"reference":[{"key":"10720_CR1","doi-asserted-by":"publisher","unstructured":"Ba JL, Kiros JR, Hinton GE (2016) Layer normalization.\u00a0https:\/\/doi.org\/10.48550\/arXiv.1607.06450","DOI":"10.48550\/arXiv.1607.06450"},{"key":"10720_CR2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1409.0473","author":"D Bahdanau","year":"2014","unstructured":"Bahdanau D, Cho K, Bengio Y (2014) Neural machine translation by jointly learning to align and translate. 3rd Int Conf Learn Represent. https:\/\/doi.org\/10.48550\/arXiv.1409.0473","journal-title":"3rd Int Conf Learn Represent"},{"key":"10720_CR3","volume-title":"Advances in neural information processing systems 13 (NIPS 2000)","author":"Y Bengio","year":"2000","unstructured":"Bengio Y, Ducharme R, Vincent P (2000) A neural probabilistic language model. In: Leen TK, Dietterich TG, Tresp V (eds) Advances in neural information processing systems 13 (NIPS 2000). The MIT Press, Cambridge"},{"key":"10720_CR4","doi-asserted-by":"publisher","DOI":"10.21203\/rs.3.rs-1200362\/v2","author":"R Bridgelall","year":"2022","unstructured":"Bridgelall R (2022) Tutorial on support vector machines. Res Square. https:\/\/doi.org\/10.21203\/rs.3.rs-1200362\/v2","journal-title":"Res Square"},{"key":"10720_CR5","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2005.14165","author":"TB Brown","year":"2020","unstructured":"Brown TB, Mann B, Ryder N, Subbiah M, Kaplan J, Dhariwal P, Amodei D (2020) Language models are few-shot learners. Adv Neural Inform Proc Syst. https:\/\/doi.org\/10.48550\/arXiv.2005.14165","journal-title":"Adv Neural Inform Proc Syst"},{"key":"10720_CR6","doi-asserted-by":"publisher","unstructured":"Bubeck S, Chandrasekaran V, Eldan R, Gehrke J, Horvitz E, Kamar E, Zhang Y (2023) Sparks of artificial general intelligence: early experiments with GPT-4.\u00a0https:\/\/doi.org\/10.48550\/arXiv.2303.12712","DOI":"10.48550\/arXiv.2303.12712"},{"key":"10720_CR7","doi-asserted-by":"publisher","unstructured":"Child R, Gray S, Radford A, Sutskever I (2019) Generating long sequences with sparse transformers.\u00a0https:\/\/doi.org\/10.48550\/arXiv.1904.10509","DOI":"10.48550\/arXiv.1904.10509"},{"key":"10720_CR8","unstructured":"Chomsky N, Roberts I, Watumull J (2023), Noam chomsky: the false promise of ChatGPT. The New York times. Accessed 8 Mar 2023. https:\/\/www.nytimes.com\/2023\/03\/08\/opinion\/noam-chomsky-chatgpt-ai.html"},{"key":"10720_CR9","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-023-10448-w","author":"Ad Garcez","year":"2023","unstructured":"Garcez Ad, Lamb LC (2023) Neurosymbolic AI: the 3rd wave. Artif Intell Rev. https:\/\/doi.org\/10.1007\/s10462-023-10448-w","journal-title":"Artif Intell Rev"},{"key":"10720_CR10","volume-title":"Hands-on machine learning with scikit-learn, keras, and tensorflow: concepts, tools, and techniques to build intelligent systems","author":"A G\u00e9ron","year":"2019","unstructured":"G\u00e9ron A (2019) Hands-on machine learning with scikit-learn, keras, and tensorflow: concepts, tools, and techniques to build intelligent systems, 2nd edn. O\u2019Reilly Media, California","edition":"2"},{"key":"10720_CR11","doi-asserted-by":"publisher","unstructured":"Geva M, Schuster R, Berant J, Levy O (2020) Transformer feed-forward layers are key-value memories.\u00a0https:\/\/doi.org\/10.48550\/arXiv.2012.14913","DOI":"10.48550\/arXiv.2012.14913"},{"key":"10720_CR12","unstructured":"Ghahramani Z (2023), Introducing PaLM 2. Google blog. Accessed 10 May 2023 from\u00a0https:\/\/blog.google\/technology\/ai\/google-palm-2-ai-large-language-model\/"},{"key":"10720_CR13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90","author":"K He","year":"2016","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. IEEE Conf Comput Vis Pattern Recogn. https:\/\/doi.org\/10.1109\/CVPR.2016.90","journal-title":"IEEE Conf Comput Vis Pattern Recogn"},{"key":"10720_CR14","doi-asserted-by":"publisher","unstructured":"Hendrycks D, Gimpel K (2016) Gaussian error linear units (GELUs).\u00a0https:\/\/doi.org\/10.48550\/arXiv.1606.08415","DOI":"10.48550\/arXiv.1606.08415"},{"issue":"5","key":"10720_CR15","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1016\/0893-6080(89)90020-8","volume":"2","author":"K Hornik","year":"1989","unstructured":"Hornik K, Stinchcombe M, White H (1989) Multilayer feedforward networks are universal approximators. Neural Netw 2(5):359\u2013366. https:\/\/doi.org\/10.1016\/0893-6080(89)90020-8","journal-title":"Neural Netw"},{"issue":"6","key":"10720_CR16","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"60","author":"A Krizhevsky","year":"2017","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2017) Imagenet classification with deep convolutional neural networks. Commun ACM 60(6):84\u201390. https:\/\/doi.org\/10.1145\/3065386","journal-title":"Commun ACM"},{"key":"10720_CR17","unstructured":"Li C (2020), OpenAI\u2019s GPT-3 Language Model: A Technical Overview. Accessed 3 June 2020\u00a0https:\/\/lambdalabs.com\/blog\/demystifying-gpt-3"},{"key":"10720_CR18","doi-asserted-by":"publisher","unstructured":"Liu Y, Han T, Ma S, Zhang J, Yang Y, Tian J, Ge B (2023) Summary of ChatGPT\/GPT-4 research and perspective towards the future of large language models. https:\/\/doi.org\/10.48550\/arXiv.2304.01852","DOI":"10.48550\/arXiv.2304.01852"},{"key":"10720_CR19","volume-title":"Foundations of statistical natural language processing","author":"C Manning","year":"1999","unstructured":"Manning C, Schutze H (1999) Foundations of statistical natural language processing. MIT Press, Cambridge"},{"key":"10720_CR20","unstructured":"Meta (2023), Introducing LLaMA: A foundational, 65-billion-parameter large language model. Meta Blog. Accessed 24 Feb 2023\u00a0https:\/\/ai.meta.com\/blog\/large-language-model-llama-meta-ai\/"},{"key":"10720_CR21","unstructured":"OpenAI. (2023), New models and developer products announced at DevDay. Accessed Dec 5 2023\u00a0\u00a0https:\/\/openai.com\/blog\/new-models-and-developer-products-announced-at-devday"},{"issue":"2","key":"10720_CR22","doi-asserted-by":"publisher","first-page":"604","DOI":"10.1109\/TNNLS.2020.2979670","volume":"32","author":"DW Otter","year":"2020","unstructured":"Otter DW, Medina JR, Kalita JK (2020) A survey of the usages of deep learning for natural language processing. IEEE Trans Neural Networks Learn Syst 32(2):604\u2013624. https:\/\/doi.org\/10.1109\/TNNLS.2020.2979670","journal-title":"IEEE Trans Neural Networks Learn Syst"},{"key":"10720_CR23","volume-title":"Advances in neural information processing systems 35\u00a0(NeurIPS 2022)","author":"L Ouyang","year":"2022","unstructured":"Ouyang L, Wu J, Jiang X, Almeida D, Wainwright C, Mishkin P, Lowe R (2022) Training language models to follow instructions with human feedback. In: Koyejo S, Mohamed S, Agarwal A, Belgrave D, Cho K, Oh A (eds) Advances in neural information processing systems 35\u00a0(NeurIPS 2022). Curran Associates Inc.,"},{"key":"10720_CR24","unstructured":"Peters J (2023), March 14 The bing AI bot has been secretly running GPT-4. The Verge. Accessed 14 Mar 2023https:\/\/www.theverge.com\/2023\/3\/14\/23639928\/microsoft-bing-chatbot-ai-gpt-4-llm"},{"key":"10720_CR25","unstructured":"Pichai S, Hassabis D (2023), Introducing Gemini: our largest and most capableAImodel. Accessed December 31 2023\u00a0https:\/\/blog.google\/technology\/ai\/google-gemini-ai\/#sundar-note"},{"key":"10720_CR26","unstructured":"Radford A, Narasimhan K, Salimans T, Sutskever I (2018) Improving language understanding by generative pre-training San Francisco, California: OpenAI. https:\/\/github.com\/openai\/finetune-transformer-lm. Accessed 7 May 2023"},{"key":"10720_CR27","unstructured":"Roose K (2022), The Brilliance and Weirdness of ChatGPT. The New York times. Accessed 5 Dec 2022https:\/\/www.nytimes.com\/2022\/12\/05\/technology\/chatgpt-ai-twitter.html. Accessed 7 May 2023"},{"key":"10720_CR28","unstructured":"Schaul K, Chen SY, Tiku N (2023), April 19 inside the secret list of websites that make AI like ChatGPT sound smart. The Washington post. Accessed April 19, 2023, from\u00a0https:\/\/www.washingtonpost.com\/technology\/interactive\/2023\/ai-chatbot-learning\/"},{"key":"10720_CR29","doi-asserted-by":"publisher","unstructured":"Sennrich R, Haddow B, Birch A (2015) Neural machine translation of rare words with subword units.\u00a0https:\/\/doi.org\/10.48550\/arXiv.1508.07909","DOI":"10.48550\/arXiv.1508.07909"},{"key":"10720_CR30","volume-title":"Oxford dictionary of English","author":"A Stevenson","year":"2010","unstructured":"Stevenson A (2010) Oxford dictionary of English. Oxford University Press, Oxford"},{"key":"10720_CR31","doi-asserted-by":"publisher","first-page":"234","DOI":"10.2307\/143141","volume":"46","author":"WR Tobler","year":"1970","unstructured":"Tobler WR (1970) A computer movie simulating urban growth in the detroit region. Econ Geogr 46:234\u2013240. https:\/\/doi.org\/10.2307\/143141","journal-title":"Econ Geogr"},{"key":"10720_CR32","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Polosukhin I (2017) Attention is all you need. In I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, & R. Garnett (Ed.), Advances in neural information processing systems 30 (NIPS 2017)\u00a0https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017. Accessed 7 May 2023"},{"key":"10720_CR33","unstructured":"W3Techs (2023), Usage of character encodings broken down by ranking. Accessed April 18 2023https:\/\/w3techs.com\/technologies\/cross\/character_encoding\/ranking"},{"key":"10720_CR34","doi-asserted-by":"publisher","DOI":"10.4018\/978-1-5225-7368-5.ch004","author":"S Walczak","year":"2019","unstructured":"Walczak S (2019) Artificial neural networks. Adv Methodol Technol Artific Intell Comput Simul Human Comput Int. https:\/\/doi.org\/10.4018\/978-1-5225-7368-5.ch004","journal-title":"Adv Methodol Technol Artific Intell Comput Simul Human Comput Int"},{"key":"10720_CR35","first-page":"24824","volume":"35","author":"J Wei","year":"2023","unstructured":"Wei J, Wang X, Schuurmans D, Bosma M, Ichter B, Xia F, Zhou D (2023) Chain-of-thought prompting elicits reasoning in large language models. Adv Neural Inform Proc Syst 35:24824\u201324837","journal-title":"Adv Neural Inform Proc Syst"},{"issue":"3","key":"10720_CR36","doi-asserted-by":"publisher","first-page":"402","DOI":"10.1111\/j.1473-4192.2007.00164.x","volume":"17","author":"H Widdowson","year":"2007","unstructured":"Widdowson H (2007) J.R. Firth, 1957, papers in linguistics 1934\u201351. Int J Appl Linguistics 17(3):402\u2013413. https:\/\/doi.org\/10.1111\/j.1473-4192.2007.00164.x","journal-title":"Int J Appl Linguistics"},{"key":"10720_CR37","unstructured":"Wolfram S (2002) A new kind of science champaign, IL: Stephen Wolfram, LLC.\u00a0https:\/\/www.wolframscience.com\/nks\/notes-8-8--zipfs-law\/. Accessed 7 May 2023"}],"container-title":["Artificial Intelligence Review"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-024-10720-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10462-024-10720-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-024-10720-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,13]],"date-time":"2024-04-13T07:10:13Z","timestamp":1712992213000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10462-024-10720-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,13]]},"references-count":37,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2024,4]]}},"alternative-id":["10720"],"URL":"https:\/\/doi.org\/10.1007\/s10462-024-10720-7","relation":{},"ISSN":["1573-7462"],"issn-type":[{"value":"1573-7462","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,13]]},"assertion":[{"value":"31 January 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 March 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The author has no conflicts of interest to declare. The author created all the figures in this primer. The author did not use AI tools to generate any portion of this document. Data sharing is not applicable to this article. The author did not receive funding for this work.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"89"}}