DCBU at GenAI Detection Task 1: Enhancing Machine-Generated Text Detection with Semantic and Probabilistic Features

Zhaowen Zhang, Songhao Chen, Bingquan Liu


Abstract
This paper presents our approach to the MGT Detection Task 1, which focuses on detecting AI-generated content. The objective of this task is to classify texts as either machine-generated or human-written. We participated in Subtask A, which concentrates on English-only texts. We utilized the RoBERTa model for semantic feature extraction and the LLaMA3 model for probabilistic feature analysis. By integrating these features, we aimed to enhance the system’s classification accuracy. Our approach achieved strong results, with an F1 score of 0.7713 on Subtask A, ranking ninth among 36 teams. These results demonstrate the effectiveness of our feature integration strategy.
Anthology ID:
2025.genaidetect-1.12
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:
150–154
Language:
URL:
https://aclanthology.org/2025.genaidetect-1.12/
DOI:
Bibkey:
Cite (ACL):
Zhaowen Zhang, Songhao Chen, and Bingquan Liu. 2025. DCBU at GenAI Detection Task 1: Enhancing Machine-Generated Text Detection with Semantic and Probabilistic Features. In Proceedings of the 1stWorkshop on GenAI Content Detection (GenAIDetect), pages 150–154, Abu Dhabi, UAE. International Conference on Computational Linguistics.
Cite (Informal):
DCBU at GenAI Detection Task 1: Enhancing Machine-Generated Text Detection with Semantic and Probabilistic Features (Zhang et al., GenAIDetect 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.genaidetect-1.12.pdf