Editing Chatbot (section)

== History ==

=== Turing test ===
In 1950, [[Alan Turing]]'s famous article "[[Computing Machinery and Intelligence]]" was published,<ref name="Turing" /> which proposed what is now called the [[Turing test]] as a criterion of [[intelligence]]. This criterion depends on the ability of a [[computer program]] to impersonate a human in a [[Real-time computing|real-time]] written conversation with a human judge to the extent that the judge is unable to distinguish reliably—on the basis of the conversational content alone—between the program and a real human.

=== Eliza ===
The notoriety of Turing's proposed test stimulated great interest in [[Joseph Weizenbaum]]'s program [[ELIZA]], published in 1966, which seemed to be able to fool users into believing that they were conversing with a real human. However Weizenbaum himself did not claim that ELIZA was genuinely intelligent, and the introduction to his paper presented it more as a debunking exercise:<blockquote>In artificial intelligence, machines are made to behave in wondrous ways, often sufficient to dazzle even the most experienced observer. But once a particular program is unmasked, once its inner workings are explained, its magic crumbles away; it stands revealed as a mere collection of procedures. The observer says to himself "I could have written that". With that thought, he moves the program in question from the shelf marked "intelligent", to that reserved for curios. The object of this paper is to cause just such a re-evaluation of the program about to be "explained". Few programs ever needed it more.<ref name="Weizenbaum" /></blockquote>ELIZA's key method of operation involves the recognition of clue words or phrases in the input, and the output of the corresponding pre-prepared or pre-programmed responses that can move the conversation forward in an apparently meaningful way (e.g. by responding to any input that contains the word 'MOTHER' with 'TELL ME MORE ABOUT YOUR FAMILY').<ref name="Weizenbaum" /> Thus an illusion of understanding is generated, even though the processing involved has been merely superficial. ELIZA showed that such an illusion is surprisingly easy to generate because human judges are ready to give the benefit of the doubt when conversational responses are ''capable of being interpreted'' as "intelligent".

Interface designers have come to appreciate that humans' readiness to interpret computer output as genuinely conversational—even when it is actually based on rather simple pattern-matching—can be exploited for useful purposes. Most people prefer to engage with programs that are human-like, and this gives chatbot-style techniques a potentially useful role in interactive systems that need to elicit information from users, as long as that information is relatively straightforward and falls into predictable categories. Thus, for example, online help systems can usefully employ chatbot techniques to identify the area of help that users require, potentially providing a "friendlier" interface than a more formal search or menu system. This sort of usage holds the prospect of moving chatbot technology from Weizenbaum's "shelf ... reserved for curios" to that marked "genuinely useful computational methods".

=== Early chatbots ===
Among the most notable early chatbots are ELIZA (1966) and [[PARRY]] (1972).<ref name="Güzeldere" /><ref name="comphis" /><ref name="Sondheim" /><ref name="rfc0439" /> More recent notable programs include [[Artificial Linguistic Internet Computer Entity|A.L.I.C.E.]], [[Jabberwacky]] and D.U.D.E ([[Agence Nationale de la Recherche]] and [[CNRS]] 2006). While ELIZA and PARRY were used exclusively to simulate typed conversation, many chatbots now include other functional features, such as games and [[Search engine|web searching]] abilities. In 1984, a book called ''The Policeman's Beard is Half Constructed'' was published, allegedly written by the chatbot [[Racter]] (though the program as released would not have been capable of doing so).<ref>[http://everything2.com/title/The+Policeman%2527s+Beard+is+Half+Constructed The Policeman's Beard is Half Constructed] {{Webarchive|url=https://web.archive.org/web/20100204175415/http://everything2.com/title/the+policeman%2527s+beard+is+half+constructed|date=4 February 2010}}. everything2.com. 13 November 1999</ref>

From 1978<ref>Kolodner, Janet L. ''[https://apps.dtic.mil/sti/citations/ADA062974 Memory organization for natural language data-base inquiry]''. Advanced Research Projects Agency, 1978.</ref> to some time after 1983,<ref name="Kolodner-19832">{{Cite journal |last=Kolodner |first=Janet L. |date=1 October 1983 |title=Maintaining organization in a dynamic long-term memory |journal=Cognitive Science |language=en |volume=7 |issue=4 |pages=243–280 |doi=10.1016/S0364-0213(83)80001-9 |doi-broken-date=5 January 2025 |issn=0364-0213 |doi-access=free}}</ref> the CYRUS project led by [[Janet Kolodner]] constructed a chatbot simulating [[Cyrus Vance]] (57th [[United States Secretary of State]]). It used [[case-based reasoning]], and updated its database daily by parsing wire news from [[United Press International]]. The program was unable to process the news items subsequent to the surprise resignation of Cyrus Vance in April 1980, and the team constructed another chatbot simulating his successor, [[Edmund Muskie]].<ref>{{Citation |last=Dennett |first=Daniel C. |title=Can Machines Think? |date=2004 |work=Alan Turing: Life and Legacy of a Great Thinker |pages=295–316 |editor-last=Teuscher |editor-first=Christof |url=https://doi.org/10.1007/978-3-662-05642-4_12 |access-date=23 July 2023 |place=Berlin, Heidelberg |publisher=Springer |language=en |doi=10.1007/978-3-662-05642-4_12 |isbn=978-3-662-05642-4|url-access=subscription }}</ref><ref name="Kolodner-19832" />

One pertinent field of AI research is [[Natural language processing|natural-language processing]]. Usually, [[Weak artificial intelligence|weak AI]] fields employ specialized software or programming languages created specifically for the narrow function required. For example, A.L.I.C.E. uses a [[markup language]] called AIML,<ref name="Caldarini-20223" /> which is specific to its function as a [[Dialogue system|conversational agent]], and has since been adopted by various other developers of, so-called, [[Alicebot]]s. Nevertheless, A.L.I.C.E. is still purely based on [[pattern matching]] techniques without any reasoning capabilities, the same technique ELIZA was using back in 1966. This is not strong AI, which would require [[sapience]] and [[logical reasoning]] abilities.

Jabberwacky learns new responses and context based on [[Real-time computing|real-time]] [[Human–computer interaction|user interactions]], rather than being driven from a static [[database]]. Some more recent chatbots also combine real-time learning with [[evolutionary algorithm]]s that optimize their ability to communicate based on each conversation held.

Chatbot competitions focus on the Turing test or more specific goals. Two such annual contests are the [[Loebner Prize]] and The Chatterbox Challenge (the latter has been offline since 2015, however, materials can still be found from web archives).<ref>{{Cite web |date=11 October 2015 |title=Chat Robots Simiulate People |url=https://pcsite.co.uk/chat-robots-simulate-people/}}</ref>

[[DBpedia]] created a chatbot during the [[Google Summer of Code|GSoC]] of 2017.<ref>{{Cite web |date=22 August 2018 |title=Meet the DBpedia Chatbot &#124; DBpedia |url=https://wiki.dbpedia.org/blog/meet-dbpedia-chatbot |url-status=live |archive-url=https://web.archive.org/web/20190902144929/https://wiki.dbpedia.org/blog/meet-dbpedia-chatbot |archive-date=2 September 2019 |access-date=2 September 2019 |website=wiki.dbpedia.org}}</ref> It can communicate through [[Facebook Messenger]].

=== Modern chatbots based on large language models ===
Modern chatbots like [[ChatGPT]] are often based on [[large language model]]s called [[generative pre-trained transformer]]s (GPT). They are based on a [[deep learning]] architecture called the [[Transformer (deep learning architecture)|transformer]], which contains [[artificial neural networks]]. They learn how to generate text by being trained on a large [[text corpus]], which provides a solid foundation for the model to perform well on downstream tasks with limited amounts of task-specific data. Despite criticism of its accuracy and tendency to "hallucinate"—that is, to confidently output false information and even cite non-existent sources—ChatGPT has gained attention for its detailed responses and historical knowledge. Another example is BioGPT, developed by [[Microsoft]], which focuses on answering [[biomedical]] questions.<ref>{{cite journal |last1=Luo |first1=Renqian |last2=Sun |first2=Liai |last3=Xia |first3=Yingce |last4=Qin |first4=Tao |last5=Zhang |first5=Sheng |last6=Poon |first6=Hoifung |last7=Liu |first7=Tie-Yan |display-authors=etal |year=2022 |title=BioGPT: generative pre-trained transformer for biomedical text generation and mining |journal=Brief Bioinform |volume=23 |issue=6 |pages= |arxiv=2210.10341 |doi=10.1093/bib/bbac409 |pmid=36156661}}</ref><ref>{{cite web |author=Bastian, Matthias |date=29 January 2023 |title=BioGPT is a Microsoft language model trained for biomedical tasks |url=https://the-decoder.com/biogpt-is-a-microsoft-language-model-trained-for-biomedical-tasks/ |url-status=live |archive-url=https://web.archive.org/web/20230207174627/https://the-decoder.com/biogpt-is-a-microsoft-language-model-trained-for-biomedical-tasks/ |archive-date=7 February 2023 |access-date=7 February 2023 |website=The Decoder}}</ref> In November 2023, Amazon announced a new chatbot, called Q, for people to use at work.<ref>{{Cite web |last=Novet |first=Jordan |date=28 November 2023 |title=Amazon announces Q, an AI chatbot for businesses |url=https://www.cnbc.com/2023/11/28/amazon-announces-q-an-ai-chatbot-for-businesses.html |access-date=28 November 2023 |website=CNBC |language=en}}</ref>