Leidos at GenAI Detection Task 3: A Weight-Balanced Transformer Approach for AI Generated Text Detection Across Domains

Abishek R. Edikala, Gregorios A. Katsios, Noelie Creaghe, Ning Yu


Abstract
Advancements in Large Language Models (LLMs) blur the distinction between human and machine-generated text (MGT), raising concerns about misinformation and academic dishonesty. Existing MGT detection methods often fail to generalize across domains and generator models. We address this by framing MGT detection as a text classification task using transformer-based models. Utilizing Distil-RoBERTa-Base, we train four classifiers (binary and multi-class, with and without class weighting) on the RAID dataset (Dugan et al., 2024). Our systems placed first to fourth in the COLING 2025 MGT Detection Challenge Task 3 (Dugan et al., 2025). Internal in-domain and zero-shot evaluations reveal that applying class weighting improves detector performance, especially with multi-class classification training. Our best model effectively generalizes to unseen domains and generators, demonstrating that transformer-based models are robust detectors of machine-generated text.
Anthology ID:
2025.genaidetect-1.39
Volume:
Proceedings of the 1stWorkshop on GenAI Content Detection (GenAIDetect)
Month:
January
Year:
2025
Address:
Abu Dhabi, UAE
Editors:
Firoj Alam, Preslav Nakov, Nizar Habash, Iryna Gurevych, Shammur Chowdhury, Artem Shelmanov, Yuxia Wang, Ekaterina Artemova, Mucahid Kutlu, George Mikros
Venues:
GenAIDetect | WS
SIG:
Publisher:
International Conference on Computational Linguistics
Note:
Pages:
340–346
Language:
URL:
https://aclanthology.org/2025.genaidetect-1.39/
DOI:
Bibkey:
Cite (ACL):
Abishek R. Edikala, Gregorios A. Katsios, Noelie Creaghe, and Ning Yu. 2025. Leidos at GenAI Detection Task 3: A Weight-Balanced Transformer Approach for AI Generated Text Detection Across Domains. In Proceedings of the 1stWorkshop on GenAI Content Detection (GenAIDetect), pages 340–346, Abu Dhabi, UAE. International Conference on Computational Linguistics.
Cite (Informal):
Leidos at GenAI Detection Task 3: A Weight-Balanced Transformer Approach for AI Generated Text Detection Across Domains (Edikala et al., GenAIDetect 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.genaidetect-1.39.pdf