A Multimodal Transformer-based Approach for Cross-Domain Detection of Machine-Generated Text

Mohammad AL-Smadi


Abstract
The rapid advancement of large language models (LLMs) has made it increasingly challenging to distinguish between human-written and machine-generated content. This paper presents IntegrityAI, a multimodal ELECTRA-based model for the detection of AI-generated text across multiple domains. Our approach combines textual features processed through a pre-trained ELECTRA model with handcrafted stylometric features to create a robust classifier. We evaluate our system on the Multi-Domain Detection of AI-Generated Text (M-DAIGT) shared task, which focuses on identifying AI-generated content in news articles and academic writing. IntegrityAI achieves exceptional performance and ranked 1st in both subtasks, with F1-scores of 99.6% and 99.9% on the news article detection and academic writing detection subtasks, respectively. Our results demonstrate the effectiveness of combining transformer-based models with stylometric analysis for detecting AI-generated content across diverse domains and writing styles.
Anthology ID:
2025.ranlp-mdaigt.4
Volume:
Proceedings of the Shared Task on Multi-Domain Detection of AI-Generated Text
Month:
September
Year:
2025
Address:
Varna, Bulgaria
Editors:
Salima Lamsiyah, Saad Ezzini, Abdelkader El Mahdaoui, Hamza Alami, Abdessamad Benlahbib, Samir El Amrani, Salmane Chafik, Hicham Hammouchi
Venues:
RANLP | WS
SIG:
Publisher:
INCOMA Ltd., Shoumen, Bulgaria
Note:
Pages:
20–25
Language:
URL:
https://aclanthology.org/2025.ranlp-mdaigt.4/
DOI:
Bibkey:
Cite (ACL):
Mohammad AL-Smadi. 2025. A Multimodal Transformer-based Approach for Cross-Domain Detection of Machine-Generated Text. In Proceedings of the Shared Task on Multi-Domain Detection of AI-Generated Text, pages 20–25, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.
Cite (Informal):
A Multimodal Transformer-based Approach for Cross-Domain Detection of Machine-Generated Text (AL-Smadi, RANLP 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.ranlp-mdaigt.4.pdf