Automatic Machine Translation Detection Using a Surrogate Multilingual Translation Model
Abstract
Modern machine translation (MT) systems depend on large parallel corpora, often collected from the Internet. However, recent evidence indicates that (i) a substantial portion of these texts are machine-generated translations, and (ii) an overreliance on such synthetic content in training data can significantly degrade translation quality. As a result, filtering out non-human translations is becoming an essential pre-processing step in building high-quality MT systems. In this work, we propose a novel approach that directly exploits the internal representations of a surrogate multilingual MT model to distinguish between human and machine-translated sentences. Experimental results show that our method outperforms current state-of-the-art techniques, particularly for non-English language pairs, achieving gains of at least 5 percentage points of accuracy.
Cite
@article{arxiv.2511.02958,
title = {Automatic Machine Translation Detection Using a Surrogate Multilingual Translation Model},
author = {Cristian García-Romero and Miquel Esplà-Gomis and Felipe Sánchez-Martínez},
journal= {arXiv preprint arXiv:2511.02958},
year = {2025}
}
Comments
Pre-MIT Press publication version