We discover a previously overlooked challenge in personalized text generation: personalization methods are increasingly applied under explicit style instructions, yet their behavior under such constraints remains poorly understood. To balance implicit personalization and explicit style, we formulate personalization as a distributional residual and propose PsPLUG, a lightweight soft-prompt plug-in trained with style-conditioned preference contrasts. Across LaMP benchmark, our framework improves persona alignment, maintains stylistic fidelity, and outperforms retrieval-based and soft-prompt baselines with minimal computation. These results show that residual modeling provides a simple and principled foundation for controllable, style-aware LLM personalization.
@article{arxiv.2601.06362,
title = {Styles + Persona-plug = Customized LLMs},
author = {Yutong Song and Jiang Wu and Shaofan Yuan and Chengze Shen and Jian Wang and Amir Rahmani and Nikil Dutt and Yu Wang},
journal= {arXiv preprint arXiv:2601.06362},
year = {2026}
}