The task of authorship style transfer involves rewriting text in the style of a target author while preserving the meaning of the original text. Existing style transfer methods train a single model on large corpora to model all target styles at once: this high-cost approach offers limited flexibility for target-specific adaptation, and often sacrifices meaning preservation for style transfer. In this paper, we propose AuthorMix: a lightweight, modular, and interpretable style transfer framework. We train individual, style-specific LoRA adapters on a small set of high-resource authors, allowing the rapid training of specialized adaptation models for each new target via learned, layer-wise adapter mixing, using only a handful of target-style training examples. AuthorMix outperforms existing, SoTA style-transfer baselines-as well as GPT-5.1-for low-resource targets, achieving the highest overall score and substantially improving meaning preservation in both automatic and human evaluations.
@article{arxiv.2603.23069,
title = {AuthorMix: Modular Authorship Style Transfer via Layer-wise Adapter Mixing},
author = {Sarubi Thillainathan and Ji-Ung Lee and Michael Sullivan and Alexander Koller},
journal= {arXiv preprint arXiv:2603.23069},
year = {2026}
}