Evaluating the authenticity of ChatGPT responses: a study on text-matching capabilities

<p dir="ltr">Academic plagiarism is a pressing concern in educational institutions. With the emergence of artificial intelligence (AI) chatbots, like ChatGPT, potential risks related to cheating and plagiarism have increased. This study aims to investigate the authenticity capabiliti...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Ahmed M. Elkhatat (14152314) (author)
منشور في: 2023
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513530506510336
author Ahmed M. Elkhatat (14152314)
author_facet Ahmed M. Elkhatat (14152314)
author_role author
dc.creator.none.fl_str_mv Ahmed M. Elkhatat (14152314)
dc.date.none.fl_str_mv 2023-08-01T00:00:00Z
dc.identifier.none.fl_str_mv 10.1007/s40979-023-00137-0
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Evaluating_the_authenticity_of_ChatGPT_responses_a_study_on_text-matching_capabilities/24999095
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Education
Specialist studies in education
Information and computing sciences
Artificial intelligence
Artifcial intelligence
Plagiarisim
Academic integrity
ChatGPT
dc.title.none.fl_str_mv Evaluating the authenticity of ChatGPT responses: a study on text-matching capabilities
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">Academic plagiarism is a pressing concern in educational institutions. With the emergence of artificial intelligence (AI) chatbots, like ChatGPT, potential risks related to cheating and plagiarism have increased. This study aims to investigate the authenticity capabilities of ChatGPT models 3.5 and 4 in generating novel, coherent, and accurate responses that evade detection by text-matching software. The repeatability and reproducibility of both models were analyzed, showing that the generation of responses remains consistent. However, a two-sample t-test revealed insufficient evidence to support a statistically significant difference between the text-matching percentages of both models. Several strategies are proposed to address the challenges posed by AI integration in academic contexts; one probable solution is to promote self-transcendent ideals by implementing honor codes. It is also necessary to consider the restricted knowledge base of AI language models like GPT and address any inaccuracies in generated references. Additionally, designing assignments that extract data from imaged sources and integrating oral discussions into the evaluation process can mitigate the challenges posed by AI integration. However, educators should carefully consider the practical constraints and explore alternative assessment methods to prevent academic misconduct while reaping the benefits of these strategies.</p><h2>Other Information</h2><p dir="ltr">Published in: International Journal for Educational Integrity<br>License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1007/s40979-023-00137-0" target="_blank">https://dx.doi.org/10.1007/s40979-023-00137-0</a></p>
eu_rights_str_mv openAccess
id Manara2_f8a00ef9897e71dba04b44e43f06e168
identifier_str_mv 10.1007/s40979-023-00137-0
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/24999095
publishDate 2023
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Evaluating the authenticity of ChatGPT responses: a study on text-matching capabilitiesAhmed M. Elkhatat (14152314)EducationSpecialist studies in educationInformation and computing sciencesArtificial intelligenceArtifcial intelligencePlagiarisimAcademic integrityChatGPT<p dir="ltr">Academic plagiarism is a pressing concern in educational institutions. With the emergence of artificial intelligence (AI) chatbots, like ChatGPT, potential risks related to cheating and plagiarism have increased. This study aims to investigate the authenticity capabilities of ChatGPT models 3.5 and 4 in generating novel, coherent, and accurate responses that evade detection by text-matching software. The repeatability and reproducibility of both models were analyzed, showing that the generation of responses remains consistent. However, a two-sample t-test revealed insufficient evidence to support a statistically significant difference between the text-matching percentages of both models. Several strategies are proposed to address the challenges posed by AI integration in academic contexts; one probable solution is to promote self-transcendent ideals by implementing honor codes. It is also necessary to consider the restricted knowledge base of AI language models like GPT and address any inaccuracies in generated references. Additionally, designing assignments that extract data from imaged sources and integrating oral discussions into the evaluation process can mitigate the challenges posed by AI integration. However, educators should carefully consider the practical constraints and explore alternative assessment methods to prevent academic misconduct while reaping the benefits of these strategies.</p><h2>Other Information</h2><p dir="ltr">Published in: International Journal for Educational Integrity<br>License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1007/s40979-023-00137-0" target="_blank">https://dx.doi.org/10.1007/s40979-023-00137-0</a></p>2023-08-01T00:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1007/s40979-023-00137-0https://figshare.com/articles/journal_contribution/Evaluating_the_authenticity_of_ChatGPT_responses_a_study_on_text-matching_capabilities/24999095CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/249990952023-08-01T00:00:00Z
spellingShingle Evaluating the authenticity of ChatGPT responses: a study on text-matching capabilities
Ahmed M. Elkhatat (14152314)
Education
Specialist studies in education
Information and computing sciences
Artificial intelligence
Artifcial intelligence
Plagiarisim
Academic integrity
ChatGPT
status_str publishedVersion
title Evaluating the authenticity of ChatGPT responses: a study on text-matching capabilities
title_full Evaluating the authenticity of ChatGPT responses: a study on text-matching capabilities
title_fullStr Evaluating the authenticity of ChatGPT responses: a study on text-matching capabilities
title_full_unstemmed Evaluating the authenticity of ChatGPT responses: a study on text-matching capabilities
title_short Evaluating the authenticity of ChatGPT responses: a study on text-matching capabilities
title_sort Evaluating the authenticity of ChatGPT responses: a study on text-matching capabilities
topic Education
Specialist studies in education
Information and computing sciences
Artificial intelligence
Artifcial intelligence
Plagiarisim
Academic integrity
ChatGPT