Skip to main navigation Skip to search Skip to main content

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

  • Zhao Wen Zhang*
  • , Songhao Chen*
  • , Bingquan Liu*
  • *Corresponding author for this work
  • Harbin Institute of Technology
  • Lenovo

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

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.

Original languageEnglish
Title of host publicationGenAIDetect 2025 - Proceedings of the 1st Workshop on GenAI Content Detection, Proceedings of the Workshop - 31st International Conference on Computational Linguistics, COLING 2025
EditorsFiroj Alam, Preslav Nakov, Nizar Habash, Iryna Gurevych, Iryna Gurevych, Shammur Chowdhury, Artem Shelmanov, Yuxia Wang, Ekaterina Artemova, Mucahid Kutlu, George Mikros
PublisherAssociation for Computational Linguistics (ACL)
Pages150-154
Number of pages5
ISBN (Electronic)9798891762053
StatePublished - 2025
Event1st Workshop on GenAI Content Detection, GenAIDetect 2025 - Abu Dhabi, United Arab Emirates
Duration: 19 Jan 2025 → …

Publication series

NameProceedings - International Conference on Computational Linguistics, COLING
ISSN (Print)2951-2093

Conference

Conference1st Workshop on GenAI Content Detection, GenAIDetect 2025
Country/TerritoryUnited Arab Emirates
CityAbu Dhabi
Period19/01/25 → …

Fingerprint

Dive into the research topics of 'DCBU at GenAI Detection Task 1: Enhancing Machine-Generated Text Detection with Semantic and Probabilistic Features'. Together they form a unique fingerprint.

Cite this