Saved in:
Bibliographic Details
Main Authors: La Cava, Lucio, Tagarelli, Andrea
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.25860
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917444246831104
author La Cava, Lucio
Tagarelli, Andrea
author_facet La Cava, Lucio
Tagarelli, Andrea
contents Machine-generated text (MGT) detection requires identifying structurally invariant signals across generation models, rather than relying on model-specific fingerprints. In this respect, we hypothesize that while large language models excel at local semantic consistency, their autoregressive nature results in a specific kind of structural fragility compared to human writing. We propose Luminol-AIDetect, a novel, zero-shot statistical approach that exposes this fragility through coherence disruption. By applying a simple randomized text-shuffling procedure, we demonstrate that the resulting shift in perplexity serves as a principled, model-agnostic discriminant, as MGT displays a characteristic dispersion in perplexity-under-shuffling that differs markedly from the more stable structural variability of human-written text. Luminol-AIDetect leverages this distinction to inform its decision process, where a handful of perplexity-based scalar features are extracted from an input text and its shuffled version, then detection is performed via density estimation and ensemble-based prediction. Evaluated across 8 content domains, 11 adversarial attack types, and 18 languages, Luminol-AIDetect demonstrates state-of-the-art performance, with gains up to 17x lower FPR while being cheaper than prior methods.
format Preprint
id arxiv_https___arxiv_org_abs_2604_25860
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Luminol-AIDetect: Fast Zero-shot Machine-Generated Text Detection based on Perplexity under Text Shuffling
La Cava, Lucio
Tagarelli, Andrea
Computation and Language
Artificial Intelligence
Computers and Society
Machine-generated text (MGT) detection requires identifying structurally invariant signals across generation models, rather than relying on model-specific fingerprints. In this respect, we hypothesize that while large language models excel at local semantic consistency, their autoregressive nature results in a specific kind of structural fragility compared to human writing. We propose Luminol-AIDetect, a novel, zero-shot statistical approach that exposes this fragility through coherence disruption. By applying a simple randomized text-shuffling procedure, we demonstrate that the resulting shift in perplexity serves as a principled, model-agnostic discriminant, as MGT displays a characteristic dispersion in perplexity-under-shuffling that differs markedly from the more stable structural variability of human-written text. Luminol-AIDetect leverages this distinction to inform its decision process, where a handful of perplexity-based scalar features are extracted from an input text and its shuffled version, then detection is performed via density estimation and ensemble-based prediction. Evaluated across 8 content domains, 11 adversarial attack types, and 18 languages, Luminol-AIDetect demonstrates state-of-the-art performance, with gains up to 17x lower FPR while being cheaper than prior methods.
title Luminol-AIDetect: Fast Zero-shot Machine-Generated Text Detection based on Perplexity under Text Shuffling
topic Computation and Language
Artificial Intelligence
Computers and Society
url https://arxiv.org/abs/2604.25860