{"title":"ChatGPT References Unveiled: Distinguishing the Reliable from the Fake","authors":"Louie Giray","doi":"10.1080/10875301.2023.2265369","DOIUrl":null,"url":null,"abstract":"AbstractThis study explored the potential of ChatGPT in the search for reliable references. Results showed that the reliability of ChatGPT's references vary across different source types. For journal articles, they were all fabricated and not compliant with APA 7 format. Webpages did not match actual existing sites. However, for books, the generated references correctly corresponded to real, existing ones. In the case of journal websites, the links within the responses were functional. Although this exploration gained interesting insights, researchers are strongly recommended not to depend on ChatGPT for references due to accuracy issues and must undertake manual, scholarly searches.Keywords: Artificial intelligenceChatGPTfake referencesinformation accuracylarge language modelsliterature reviewreferencesscholarly research Disclosure statementNo potential conflict of interest was reported by the author(s).","PeriodicalId":35377,"journal":{"name":"Internet Reference Services Quarterly","volume":"67 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Internet Reference Services Quarterly","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1080/10875301.2023.2265369","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"Social Sciences","Score":null,"Total":0}
引用次数: 1
Abstract
AbstractThis study explored the potential of ChatGPT in the search for reliable references. Results showed that the reliability of ChatGPT's references vary across different source types. For journal articles, they were all fabricated and not compliant with APA 7 format. Webpages did not match actual existing sites. However, for books, the generated references correctly corresponded to real, existing ones. In the case of journal websites, the links within the responses were functional. Although this exploration gained interesting insights, researchers are strongly recommended not to depend on ChatGPT for references due to accuracy issues and must undertake manual, scholarly searches.Keywords: Artificial intelligenceChatGPTfake referencesinformation accuracylarge language modelsliterature reviewreferencesscholarly research Disclosure statementNo potential conflict of interest was reported by the author(s).
期刊介绍:
Internet Reference Services Quarterly tackles the tough job of keeping librarians up to date with the latest developments in Internet referencing and librarianship. This peer-reviewed quarterly journal is designed to function as a comprehensive information source librarians can turn to and count on for keeping up-to-date on emerging technological innovations, while emphasizing theoretical, research, and practical applications of Internet-related information services, sources, and resources. Librarians from any size or type of library in any discipline get the knowledge needed on how to best improve service through one of the most powerful reference tools available on the Internet.