Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Almeida, Leonardo, Rodrigues, Pedro, Magalhães, Diogo, Pinho, Armando J., Pratas, Diogo
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2411.19869
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917852228878336
author Almeida, Leonardo
Rodrigues, Pedro
Magalhães, Diogo
Pinho, Armando J.
Pratas, Diogo
author_facet Almeida, Leonardo
Rodrigues, Pedro
Magalhães, Diogo
Pinho, Armando J.
Pratas, Diogo
contents This paper introduces AIDetx, a novel method for detecting machine-generated text using data compression techniques. Traditional approaches, such as deep learning classifiers, often suffer from high computational costs and limited interpretability. To address these limitations, we propose a compression-based classification framework that leverages finite-context models (FCMs). AIDetx constructs distinct compression models for human-written and AI-generated text, classifying new inputs based on which model achieves a higher compression ratio. We evaluated AIDetx on two benchmark datasets, achieving F1 scores exceeding 97% and 99%, respectively, highlighting its high accuracy. Compared to current methods, such as large language models (LLMs), AIDetx offers a more interpretable and computationally efficient solution, significantly reducing both training time and hardware requirements (e.g., no GPUs needed). The full implementation is publicly available at https://github.com/AIDetx/AIDetx.
format Preprint
id arxiv_https___arxiv_org_abs_2411_19869
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle AIDetx: a compression-based method for identification of machine-learning generated text
Almeida, Leonardo
Rodrigues, Pedro
Magalhães, Diogo
Pinho, Armando J.
Pratas, Diogo
Computation and Language
Machine Learning
This paper introduces AIDetx, a novel method for detecting machine-generated text using data compression techniques. Traditional approaches, such as deep learning classifiers, often suffer from high computational costs and limited interpretability. To address these limitations, we propose a compression-based classification framework that leverages finite-context models (FCMs). AIDetx constructs distinct compression models for human-written and AI-generated text, classifying new inputs based on which model achieves a higher compression ratio. We evaluated AIDetx on two benchmark datasets, achieving F1 scores exceeding 97% and 99%, respectively, highlighting its high accuracy. Compared to current methods, such as large language models (LLMs), AIDetx offers a more interpretable and computationally efficient solution, significantly reducing both training time and hardware requirements (e.g., no GPUs needed). The full implementation is publicly available at https://github.com/AIDetx/AIDetx.
title AIDetx: a compression-based method for identification of machine-learning generated text
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2411.19869