Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

MGT-Prism: Enhancing Domain Generalization for Machine-Generated Text Detection via Spectral Alignment

About

Large Language Models have shown growing ability to generate fluent and coherent texts that are highly similar to the writing style of humans. Current detectors for Machine-Generated Text (MGT) perform well when they are trained and tested in the same domain but generalize poorly to unseen domains, due to domain shift between data from different sources. In this work, we propose MGT-Prism, an MGT detection method from the perspective of the frequency domain for better domain generalization. Our key insight stems from analyzing text representations in the frequency domain, where we observe consistent spectral patterns across diverse domains, while significant discrepancies in magnitude emerge between MGT and human-written texts (HWTs). The observation initiates the design of a low frequency domain filtering module for filtering out the document-level features that are sensitive to domain shift, and a dynamic spectrum alignment strategy to extract the task-specific and domain-invariant features for improving the detector's performance in domain generalization. Extensive experiments demonstrate that MGT-Prism outperforms state-of-the-art baselines by an average of 0.90% in accuracy and 0.92% in F1 score on 11 test datasets across three domain-generalization scenarios.

Shengchao Liu, Xiaoming Liu, Chengzhengxu Li, Zhaohan Zhang, Guoxin Ma, Yu Lan, Shuai Xiao• 2025

Related benchmarks

TaskDatasetResultRank
Machine-generated text detectionSQuAD--
30
MGT detectionHSWAG
Accuracy96.28
16
MGT detectionCMV
Accuracy89.08
16
MGT detectionWP
Accuracy88.58
16
MGT detectionELI5
Accuracy87.34
16
MGT detectionROCT
Accuracy65.47
16
MGT detectionXsum
Accuracy88.76
16
MGT detectionYelp
Accuracy91.14
16
MGT detectionSCI
Accuracy91.93
16
MGT detectionTLDR
Accuracy70.53
16
Showing 10 of 23 rows

Other info

Follow for update