<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>The ability of chatbots to produce plausible, human-like responses raises questions about the extent of their similarity with original texts. Using a modified version of Halliday’s clause-complexing framework, this study compared 50 abstracts of scientific research articles from Nature with generated versions produced by Bard, ChatGPT, and Poe Assistant. None of the chatbots matched the original abstracts in all categories. The only chatbot that came closest was ChatGPT, but differences in the use of finite adverbial clauses and –<italic>ing</italic> elaborating clauses were detected. Incorporating distinct grammatical features in the algorithms of AI-detection tools is crucially needed to enhance the reliability of their results. A genre-based approach to detecting AI-generated content is recommended.</p>
</abstract>

The ability of chatbots to produce plausible, human-like responses raises questions about the extent of their similarity with original texts. Using a modified version of Halliday’s clause-complexing framework, this study compared 50 abstracts of scientific research articles from Nature with generated versions produced by Bard, ChatGPT, and Poe Assistant. None of the chatbots matched the original abstracts in all categories. The only chatbot that came closest was ChatGPT, but differences in the use of finite adverbial clauses and –ing elaborating clauses were detected. Incorporating distinct grammatical features in the algorithms of AI-detection tools is crucially needed to enhance the reliability of their results. A genre-based approach to detecting AI-generated content is recommended.

Clause complexing in research-article abstracts:  Comparing human- and AI-generated texts

ExELL

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

The ability of chatbots to produce plausible, human-like responses raises questions about the extent of their similarity with original texts. Using a modified...

Clause complexing in research-article abstracts: Comparing human- and AI-generated texts

Published Online: Dec 06, 2023

Page range: 99 - 132

Received: Aug 12, 2023

Accepted: Oct 26, 2023

DOI: https://doi.org/10.2478/exell-2023-0008

Keywords
abstracts, clause complexing, generative AI, Bard, ChatGPT, Poe Assistant

© 2023 Alvin Ping Leong, published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Clause complexing in research-article abstracts: Comparing human- and AI-generated texts

Published Online: Dec 06, 2023

Page range: 99 - 132

Received: Aug 12, 2023

Accepted: Oct 26, 2023

DOI: https://doi.org/10.2478/exell-2023-0008

Keywordsabstracts, clause complexing, generative AI, Bard, ChatGPT, Poe Assistant

© 2023 Alvin Ping Leong, published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Keywords
abstracts, clause complexing, generative AI, Bard, ChatGPT, Poe Assistant