TY  - JOUR
AU  - Hassanipour, Soheil
AU  - Nayak, Sandeep
AU  - Bozorgi, Ali
AU  - Keivanlou, Mohammad-Hossein
AU  - Dave, Tirth
AU  - Alotaibi, Abdulhadi
AU  - Joukar, Farahnaz
AU  - Mellatdoust, Parinaz
AU  - Bakhshi, Arash
AU  - Kuriyakose, Dona
AU  - Polisetty, Lakshmi D
AU  - Chimpiri, Mallika
AU  - Amini-Salehi, Ehsan
PY  - 2024
DA  - 2024/7/8
TI  - The Ability of ChatGPT in Paraphrasing Texts and Reducing Plagiarism: A Descriptive Analysis
JO  - JMIR Med Educ
SP  - e53308
VL  - 10
KW  - ChatGPT
KW  - paraphrasing
KW  - text generation
KW  - prompts
KW  - academic journals
KW  - plagiarize
KW  - plagiarism
KW  - paraphrase
KW  - wording
KW  - LLM
KW  - LLMs
KW  - language model
KW  - language models
KW  - prompt
KW  - generative
KW  - artificial intelligence
KW  - NLP
KW  - natural language processing
KW  - rephrase
KW  - plagiarizing
KW  - honesty
KW  - integrity
KW  - texts
KW  - text
KW  - textual
KW  - generation
KW  - large language model
KW  - large language models
AB  - Background: The introduction of ChatGPT by OpenAI has garnered significant attention. Among its capabilities, paraphrasing stands out. Objective: This study aims to investigate the satisfactory levels of plagiarism in the paraphrased text produced by this chatbot. Methods: Three texts of varying lengths were presented to ChatGPT. ChatGPT was then instructed to paraphrase the provided texts using five different prompts. In the subsequent stage of the study, the texts were divided into separate paragraphs, and ChatGPT was requested to paraphrase each paragraph individually. Lastly, in the third stage, ChatGPT was asked to paraphrase the texts it had previously generated. Results: The average plagiarism rate in the texts generated by ChatGPT was 45% (SD 10%). ChatGPT exhibited a substantial reduction in plagiarism for the provided texts (mean difference −0.51, 95% CI −0.54 to −0.48; P<.001). Furthermore, when comparing the second attempt with the initial attempt, a significant decrease in the plagiarism rate was observed (mean difference −0.06, 95% CI −0.08 to −0.03; P<.001). The number of paragraphs in the texts demonstrated a noteworthy association with the percentage of plagiarism, with texts consisting of a single paragraph exhibiting the lowest plagiarism rate (P<.001). Conclusion: Although ChatGPT demonstrates a notable reduction of plagiarism within texts, the existing levels of plagiarism remain relatively high. This underscores a crucial caution for researchers when incorporating this chatbot into their work. 
SN  - 2369-3762
UR  - https://mededu.jmir.org/2024/1/e53308
UR  - https://doi.org/10.2196/53308
DO  - 10.2196/53308
ID  - info:doi/10.2196/53308
ER  -