Quantifying the Risks of LLM- and Tool-assisted Rephrasing to Linguistic Diversity

Mengying Wang, Andreas Spitz


Abstract
Writing assistants and large language models see widespread use in the creation of text content. While their effectiveness for individual users has been evaluated in the literature, little is known about their proclivity to change language or reduce its richness when adopted by a large user base. In this paper, we take a first step towards quantifying this risk by measuring the semantic and vocabulary change enacted by the use of rephrasing tools on a multi-domain corpus of human-generated text.
Anthology ID:
2025.findings-emnlp.1228
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2025
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
22561–22574
Language:
URL:
https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.1228/
DOI:
10.18653/v1/2025.findings-emnlp.1228
Bibkey:
Cite (ACL):
Mengying Wang and Andreas Spitz. 2025. Quantifying the Risks of LLM- and Tool-assisted Rephrasing to Linguistic Diversity. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 22561–22574, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
Quantifying the Risks of LLM- and Tool-assisted Rephrasing to Linguistic Diversity (Wang & Spitz, Findings 2025)
Copy Citation:
PDF:
https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.1228.pdf
Checklist:
 2025.findings-emnlp.1228.checklist.pdf