On Improving the Efficiency of AI-Generated Text Detection

Bogdan Ichim, Bogdan Ichim, Andrei-Cristian Năstase

2025

Abstract

This paper proposes methods of making AI-Generated Text Detectors more computationally efficient without paying a high price in prediction accuracy. Most AI-Detectors use transformer-based architectures with high-dimensional text embedding vectors involved in the pipelines. Applying dimension reduction algorithms to these vectors is a simple idea for making the whole process more efficient. Our experimental results reveal that this may lead from 5 up to 500 times improvements in the training and inference times, with only marginal performance degradation. These findings suggest that integrating such methods in largescale systems could be an excellent way to enhance the processing speed (and also reduce the electric energy consumption). In particular, real-time applications might benefit from such enhancements.

Paper Citation

in Harvard Style

Ichim B. and Năstase A. (2025). On Improving the Efficiency of AI-Generated Text Detection. In Proceedings of the 20th International Conference on Evaluation of Novel Approaches to Software Engineering - Volume 1: ENASE; ISBN 978-989-758-742-9, SciTePress, pages 731-738. DOI: 10.5220/0013433600003928

in Bibtex Style

@conference{enase25,
author={Bogdan Ichim and Andrei-Cristian Năstase},
title={On Improving the Efficiency of AI-Generated Text Detection},
booktitle={Proceedings of the 20th International Conference on Evaluation of Novel Approaches to Software Engineering - Volume 1: ENASE},
year={2025},
pages={731-738},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013433600003928},
isbn={978-989-758-742-9},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 20th International Conference on Evaluation of Novel Approaches to Software Engineering - Volume 1: ENASE
TI - On Improving the Efficiency of AI-Generated Text Detection
SN - 978-989-758-742-9
AU - Ichim B.
AU - Năstase A.
PY - 2025
SP - 731
EP - 738
DO - 10.5220/0013433600003928
PB - SciTePress