TurQUaz at GenAI Detection Task 1:Dr. Perplexity or: How I Learned to Stop Worrying and Love the Finetuning

Kaan Efe Keleş, Mucahid Kutlu


Abstract
This paper details our methods for addressing Task 1 of the GenAI Content Detection shared tasks, which focus on distinguishing AI-generated text from human-written content. The task comprises two subtasks: Subtask A, centered on English-only datasets, and Subtask B, which extends the challenge to multilingual data. Our approach uses a fine-tuned XLM-RoBERTa model for classification, complemented by features including perplexity and TF-IDF. While perplexity is commonly regarded as a useful indicator for identifying machine-generated text, our findings suggest its limitations in multi-model and multilingual contexts. Our approach ranked 6th in Subtask A, but a submission issue left our Subtask B unranked, where it would have placed 23rd.
Anthology ID:
2025.genaidetect-1.24
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:
225–229
Language:
URL:
https://aclanthology.org/2025.genaidetect-1.24/
DOI:
Bibkey:
Cite (ACL):
Kaan Efe Keleş and Mucahid Kutlu. 2025. TurQUaz at GenAI Detection Task 1:Dr. Perplexity or: How I Learned to Stop Worrying and Love the Finetuning. In Proceedings of the 1stWorkshop on GenAI Content Detection (GenAIDetect), pages 225–229, Abu Dhabi, UAE. International Conference on Computational Linguistics.
Cite (Informal):
TurQUaz at GenAI Detection Task 1:Dr. Perplexity or: How I Learned to Stop Worrying and Love the Finetuning (Keleş & Kutlu, GenAIDetect 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.genaidetect-1.24.pdf