Papers
arxiv:2606.10099

Unsupervised Style Representation Learning for AI-Text Detection via Paraphrase Inversion

Published on Jun 8
Authors:
,
,

Abstract

Unsupervised style encoding through text reconstruction enables robust detection of machine-generated content with competitive performance across few-shot and zero-shot settings.

The rapid development of large language models (LLMs) has raised concerns about misuse such as plagiarism, misinformation, and automated influence operations, motivating the need for robust detectors. Recent work has shown that neural representations of writing style are effective for detection and, crucially, robust to adversarial attacks that defeat most existing detectors. However, current style-based detectors rely on authorship labels for training, and are limited to few-shot inference for detection, requiring in-distribution samples that may not always be available. We learn discriminative style features without authorship labels by training a style encoder to reconstruct human-authored text from its machine-generated paraphrase; freezing a semantic encoder during training biases the style encoder to capture only the non-semantic features needed for reconstruction. We evaluate the learned representations via two detection strategies: a few-shot detector and a zero-shot DeepSVDD-based detector. Across benchmarks, our method matches or outperforms all baselines in the few-shot setting and, in the zero-shot regime, is competitive with fully supervised classifiers on in-distribution test data while generalizing better to unseen LLMs. Beyond detection, the learned representations generalize to unseen tasks, achieving competitive performance on authorship verification and fine-grained style discrimination despite never being trained on either objective.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2606.10099
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 1

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2606.10099 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2606.10099 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.