Humanization of AI-generated abstracts in oral radiology: Role of chatbots and dedicated platforms.

Authors

Caio Alencar-Palha, Thaís Ocampo, Thaísa Pinheiro Silva, Deborah Queiroz Freitas, Frederico Sampaio Neves, Matheus Lima Oliveira

Published in

Brazilian oral research. Volume 40. Pages e067. Epub Aug 21, 2026.

Abstract

The rise of generative artificial intelligence (AI) in scientific writing has prompted the development of platforms designed to "humanize" AI-generated text by rephrasing content to reduce its detectability as machine-generated. This study aimed to evaluate the performance of chatbots and dedicated platforms in humanizing AI-generated abstracts. Thirty high-impact scientific articles published in dentomaxillofacial radiology journals were selected. The Methodology and Results sections of each abstract were used to prompt two chatbots-ChatGPT and Gemini-to generate complete abstracts. These AI-generated abstracts were then humanized using the same chatbots along with two dedicated platforms: HumanizeAI and StealthWriter. The percentage of AI-generated content was determined for all abstracts (n = 330), including the original human-written abstracts, using GPTZero. AI detection rates were compared using two-way analysis of variance followed by Tukey's post hoc test (α = 0.05). The results showed that original abstracts and AI-generated abstracts humanized by HumanizeAI and StealthWriter exhibited significantly lower GPTZero detection rates (p < 0.05), whereas abstracts generated or humanized by chatbots showed significantly higher detection rates (p < 0.05). In conclusion, chatbot-generated scientific abstracts humanized by dedicated platforms exhibit low AI detection rates, whereas those humanized by chatbots exhibit considerably higher detection levels. Educators must prepare students with critical appraisal skills to identify AI-generated content and uphold academic integrity, ensuring that AI serves as a complementary tool rather than a means of misrepresentation.

PMID:
42659519
Bibliographic data and abstract were imported from PubMed on 28 Aug 2026.

Read full publication at:
Please sign in to see all details.

Stats

1-terrible, 9-excellent. How would you rate this publication? Sign in in to submit your rating.

Post a comment

You need to be signed in to post comments. You can sign in here.

Comments

There are no comments yet.