cs.CLNov 16, 2026

EDITORS Know Your Style! Editing LoRA Subspaces for Stylistic Attribution and Imitation

Authors: Zixuan Wang, Gregory Kang Ruey Lau, Xiao Tian, Jue Fan, Caroline Chaux, Bryan Kian Hsiang Low

Organizations: School of Computing, National University of Singapore, Singapore · Agency for Science, Technology and Research (A*STAR), Singapore · Aix Marseille Univ, CNRS, I2M, Marseille, France

Abstract

Disentangling writing style from semantic content is a fundamental challenge in literary text modeling. Style-content entanglement causes models to rely on semantic content for authorship attribution (AA) tasks and memorize author-specific content for style imitation (SI) tasks. We propose EDITORS (EditingLoRA Subspaces), a diagnose-then-deflate framework that adapts pretrained large language models and prioritizes stylistic features, making it effective for both AA and SI tasks. EDITORS first trains a diagnostic LoRA adapter using style-neutral statements derived from the training corpus to identify a content-oriented subspace. It then trains the final style adapter under activation-space deflation that projects input activations away from the identified content-oriented directions. We empirically demonstrate that EDITORS is effective. On three AA benchmarks spanning literature, social media, and news, EDITORS achieves state-of-the-art accuracy, outperforming the strongest existing baseline by up to 29%. On SI, EDITORS generates stylistically faithful and diverse passages, outperforming baselines in achieving style similarity while adhering to content specifications.

Figures & tables

Appendix figures & tables15 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. AuthorMix: Modular Authorship Style Transfer via Layer-wise Adapter Mixing

    Mar 24, 2026Sarubi Thillainathan, Ji-Ung Lee, Michael Sullivan +1Text Style TransferText Generation

  2. One-shot Style Transfer LLM log-probabilities for Authorship Attribution and Verification

    Oct 15, 2025Pablo Miralles-González, Javier Huertas-Tato, Alejandro Martín +1StylometryAuthorship Attribution

  3. Can Activation Steering Capture Multidimensional Authorship Style?

    Sep 4, 2026Hieu Tran, Calvin Bao, Marine CarpuatLanguage Model SteeringActivation Steering