arXiv cs.CL· Zixuan Wang, Gregory Kang Ruey Lau, Xiao Tian, Jue Fan, Caroline Chaux, Bryan Kian Hsiang Low·· 10 小时前AI 评分30
EDITORS:用 LoRA 子空间编辑实现写作风格归因与模仿
EDITORS Know Your Style! Editing LoRA Subspaces for Stylistic Attribution and Imitation
AI 导读
EDITORS 是一个“先诊断再消减”的框架,通过训练诊断性 LoRA 适配器定位内容导向子空间,再在激活空间消减中训练风格适配器,使预训练大语言模型优先捕捉风格特征。在文学、社交媒体和新闻三个作者归因基准上,EDITORS 取得 SOTA 准确率,最高超过最强基线 29%。在风格模仿任务上,它生成的文本风格相似且多样,同时符合内容要求。
正文 · 原文
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.
| Comments: | NeurIPS 2026 |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.20846 [cs.CL] |
| (or arXiv:2611.20846v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2611.20846 arXiv-issued DOI via DataCite |
Submission history
From: Zixuan Wang [view email]
[v1]
Mon, 16 Nov 2026 10:22:39 UTC (2,347 KB)
[v2]
Thu, 19 Nov 2026 07:45:54 UTC (2,347 KB)
来源:arXiv cs.CL · arxiv.org