Increasing the Robustness of the Fine-tuned Multilingual Machine-Generated Text Detectors

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Macko, Dominik, Moro, Robert, Srba, Ivan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916656831266816
author Macko, Dominik
Moro, Robert
Srba, Ivan
author_facet Macko, Dominik
Moro, Robert
Srba, Ivan
contents Since the proliferation of LLMs, there have been concerns about their misuse for harmful content creation and spreading. Recent studies justify such fears, providing evidence of LLM vulnerabilities and high potential of their misuse. Humans are no longer able to distinguish between high-quality machine-generated and authentic human-written texts. Therefore, it is crucial to develop automated means to accurately detect machine-generated content. It would enable to identify such content in online information space, thus providing an additional information about its credibility. This work addresses the problem by proposing a robust fine-tuning process of LLMs for the detection task, making the detectors more robust against obfuscation and more generalizable to out-of-distribution data.
format Preprint
id arxiv_https___arxiv_org_abs_2503_15128
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Increasing the Robustness of the Fine-tuned Multilingual Machine-Generated Text Detectors
Macko, Dominik
Moro, Robert
Srba, Ivan
Computation and Language
Artificial Intelligence
Since the proliferation of LLMs, there have been concerns about their misuse for harmful content creation and spreading. Recent studies justify such fears, providing evidence of LLM vulnerabilities and high potential of their misuse. Humans are no longer able to distinguish between high-quality machine-generated and authentic human-written texts. Therefore, it is crucial to develop automated means to accurately detect machine-generated content. It would enable to identify such content in online information space, thus providing an additional information about its credibility. This work addresses the problem by proposing a robust fine-tuning process of LLMs for the detection task, making the detectors more robust against obfuscation and more generalizable to out-of-distribution data.
title Increasing the Robustness of the Fine-tuned Multilingual Machine-Generated Text Detectors
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2503.15128