Detection of AI-generated Content in Scientific Abstracts

Ernesto Luis Estevanell-Valladares, Alicia Picazo-Izquierdo, Ruslan Mitkov


Abstract
The growing use of generative AI in academic writing raises urgent questions about authorship and the integrity of scientific communication. This study addresses the detection of AI-generated scientific abstracts by constructing a temporally anchored dataset of paired abstracts—each with a human-written version that contains scientific abstracts of works published before 2021 and a synthetic version generated using GPT-4.1. We evaluate three approaches to authorship classification: zero-shot large language models (LLMs), fine-tuned encoder-based transformers, and traditional machine learning classifiers. Results show that LLMs perform near chance level, while a LoRA-fine-tuned DistilBERT and a PassiveAggressive classifier achieve near-perfect performance. These findings suggest that shallow lexical or stylistic patterns still differentiate human and AI writing, and that supervised learning is key to capturing these signals.
Anthology ID:
2025.r2lm-1.3
Volume:
Proceedings of the First Workshop on Comparative Performance Evaluation: From Rules to Language Models
Month:
September
Year:
2025
Address:
Varna, Bulgaria
Editors:
Alicia Picazo-Izquierdo, Ernesto Luis Estevanell-Valladares, Ruslan Mitkov, Rafael Muñoz Guillena, Raúl García Cerdá
Venues:
R2LM | WS
SIG:
Publisher:
INCOMA Ltd., Shoumen, Bulgaria
Note:
Pages:
21–29
Language:
URL:
https://aclanthology.org/2025.r2lm-1.3/
DOI:
Bibkey:
Cite (ACL):
Ernesto Luis Estevanell-Valladares, Alicia Picazo-Izquierdo, and Ruslan Mitkov. 2025. Detection of AI-generated Content in Scientific Abstracts. In Proceedings of the First Workshop on Comparative Performance Evaluation: From Rules to Language Models, pages 21–29, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.
Cite (Informal):
Detection of AI-generated Content in Scientific Abstracts (Estevanell-Valladares et al., R2LM 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.r2lm-1.3.pdf