@inproceedings{estevanell-valladares-etal-2025-detection,
    title = "Detection of {AI}-generated Content in Scientific Abstracts",
    author = "Estevanell-Valladares, Ernesto Luis  and
      Picazo-Izquierdo, Alicia  and
      Mitkov, Ruslan",
    editor = "Picazo-Izquierdo, Alicia  and
      Estevanell-Valladares, Ernesto Luis  and
      Mitkov, Ruslan  and
      Guillena, Rafael Mu{\~n}oz  and
      Cerd{\'a}, Ra{\'u}l Garc{\'i}a",
    booktitle = "Proceedings of the First Workshop on Comparative Performance Evaluation: From Rules to Language Models",
    month = sep,
    year = "2025",
    address = "Varna, Bulgaria",
    publisher = "INCOMA Ltd., Shoumen, Bulgaria",
    url = "https://preview.aclanthology.org/corrections-2026-01/2025.r2lm-1.3/",
    pages = "21--29",
    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."
}