@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://aclanthology.org/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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="estevanell-valladares-etal-2025-detection">
<titleInfo>
<title>Detection of AI-generated Content in Scientific Abstracts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ernesto</namePart>
<namePart type="given">Luis</namePart>
<namePart type="family">Estevanell-Valladares</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alicia</namePart>
<namePart type="family">Picazo-Izquierdo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Comparative Performance Evaluation: From Rules to Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alicia</namePart>
<namePart type="family">Picazo-Izquierdo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ernesto</namePart>
<namePart type="given">Luis</namePart>
<namePart type="family">Estevanell-Valladares</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rafael</namePart>
<namePart type="given">Muñoz</namePart>
<namePart type="family">Guillena</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raúl</namePart>
<namePart type="given">García</namePart>
<namePart type="family">Cerdá</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">estevanell-valladares-etal-2025-detection</identifier>
<location>
<url>https://aclanthology.org/2025.r2lm-1.3/</url>
</location>
<part>
<date>2025-09</date>
<extent unit="page">
<start>21</start>
<end>29</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Detection of AI-generated Content in Scientific Abstracts
%A Estevanell-Valladares, Ernesto Luis
%A Picazo-Izquierdo, Alicia
%A Mitkov, Ruslan
%Y Picazo-Izquierdo, Alicia
%Y Estevanell-Valladares, Ernesto Luis
%Y Mitkov, Ruslan
%Y Guillena, Rafael Muñoz
%Y Cerdá, Raúl García
%S Proceedings of the First Workshop on Comparative Performance Evaluation: From Rules to Language Models
%D 2025
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F estevanell-valladares-etal-2025-detection
%X 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.
%U https://aclanthology.org/2025.r2lm-1.3/
%P 21-29
Markdown (Informal)
[Detection of AI-generated Content in Scientific Abstracts](https://aclanthology.org/2025.r2lm-1.3/) (Estevanell-Valladares et al., R2LM 2025)
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.