To read this content please select one of the options below:

Does ChatGPT generate fake results? Challenges in retrieving content through ChatGPT

Muhammad Safdar (Gad and Birgit Rausing Library, Lahore University of Management Sciences, Lahore, Pakistan)
Nadeem Siddique (Gad and Birgit Rausing Library, Lahore University of Management Sciences, Lahore, Pakistan)
Ayesha Gulzar (University of Sargodha, Sargodha, Pakistan)
Haisim Yasin (Systems Limited, Lahore, Pakistan)
Muhammad Ajmal Khan (Imam Abdulrahman Bin Faisal University, Dammam, Saudi Arabia)

Digital Library Perspectives

ISSN: 2059-5816

Article publication date: 5 August 2024

Issue publication date: 29 October 2024

190

Abstract

Purpose

ChatGPT is a new development in this technological era. This artificial intelligence-based tool responds to individuals’ queries and produces the requested content within seconds. Therefore, it is becoming popular among academics, the research community and library professionals. This study aims to test (through personal interaction with the tool) the authenticity of the ChatGPT’s produced records. Another objective of the research is to check the relevance between the individuals’ queries and the tool’s results. The research also intends to identify the challenges in retrieving information through ChatGPT.

Design/methodology/approach

The five researchers from different countries and organizations experienced ChatGPT by asking questions on more than 70 subjects. The responses were recorded in Notepad and converted into MS Excel and MS Access to standardize and analyze the data. The investigators consulted 11 reputed databases/sources, including Web of Science and Scopus, to assess the authenticity of the data retrieved through ChatGPT.

Findings

The findings confirmed that over 90% of results produced by ChatGPT were fake (the information did not exist in the literature). Similarly, the study sheds light on the discrepancies, such as irrelevant and incomplete information in the data generated by ChatGPT.

Originality/value

This is a unique study that shares the findings based on the different regions’ researchers’ personal experiences with ChatGPT. The researchers covered different subject areas (above 70) while asking questions to ChatGPT. The paper shares implications for researchers, students, faculty members, academic/research organizations and policymakers.

Keywords

Acknowledgements

It has come to the attention of the publisher that the article, Muhammad Safdar, Nadeem Siddique, Ayesha Gulzar, Haisim Yasin and Muhammad Ajmal Khan “Does ChatGPT generate fake results? Challenges in retrieving content through ChatGPT”, published in Digital Library Perspectives, Vol. ahead-of-print No. ahead-of-print, was published with misleading affiliation information for Muhammad Safdar and Nadeem Siddique. The correct affiliation information is Gad and Birgit Rausing Library, Lahore University of Management Sciences, Lahore, Pakistan. The error was introduced in the editorial process and has now been corrected in the online version. The publisher sincerely apologises for these errors and for any inconvenience caused.

Funding: The authors did not receive any kind of funding from any source for this paper.

Conflict of interest: The authors declare that there is no conflict of interest.

Citation

Safdar, M., Siddique, N., Gulzar, A., Yasin, H. and Khan, M.A. (2024), "Does ChatGPT generate fake results? Challenges in retrieving content through ChatGPT", Digital Library Perspectives, Vol. 40 No. 4, pp. 668-680. https://doi.org/10.1108/DLP-01-2024-0006

Publisher

:

Emerald Publishing Limited

Copyright © 2024, Emerald Publishing Limited

Related articles