Turquaz at Genai Detection Task 1: Dr. Perplexity Or: How I Learned To Stop Worrying and Love the Finetuning

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. © 2025 International Conference on Computational Linguistics.