Controlling stylistic attributes in large language models (LLMs) remains challenging, with existing approaches relying on either prompt engineering or post-training alignment. This paper investigates this challenge through the lens of representation engineering, testing the hypothesis that distinct stylistic attributes - from emotional tone to linguistic structure - are encoded as linear directions in the model's activation space. We provide strong empirical evidence for this hypothesis across a wide range of styles and, based on this finding, present a lightweight, training-free method for precise style control. Our approach supports linear style composition, enhances safety by ablating undesirable behaviors, and, as confirmed by experiments on over a dozen models, achieves high style adherence while preserving core capabilities at minimal computational cost.
ChatGPT-powered Conversational Drug Editing Using Retrieval and Domain Feedback
Mila-Québec Artificial Intelligence Institute（米拉-魁北克人工智能研究所）；Arizona State University（亚利桑那州立大学）；Princeton University（普林斯顿大学）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Université de Montréal（蒙特利尔大学）；National Research Council Canada（加拿大国家研究委员会）
From Completion to Editing: Unlocking Context-Aware Code Infilling via Search-and-Replace Instruction Tuning
USTC（University of Science and Technology of China）；Alibaba Group（阿里巴巴集团）；CASIA（Chinese Academy of Sciences Institute of Automation）；SIAT（Institute of Automation, Chinese Academy of Sciences）
EtCon: Edit-then-Consolidate for Reliable Knowledge Editing
Wuhan University（武汉大学）；Shanghai Innovation Institute（上海创新研究院）；Fudan University（复旦大学）；Shanghai Jiao Tong University（上海交通大学）；University of Science and Technology of China（中国科学技术大学）
Generalizable Model Editing Could Be More Than Direct Generalization
University of Cambridge（剑桥大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of the Chinese Academy of Sciences（中国科学院大学）；HUST（华中科技大学）；BUPT（北京邮电大学）；Shandong University（山东大学）
Beyond the Sentence: A Survey on Context-Aware Machine Translation with Large Language Models
Department of Computer Science and Engineering, Indian Institute of Technology Patna, India（印度理工学院帕纳瓦分校计算机科学与工程系）；Wipro AI, Lab45, London, UK（Wipro AI，Lab45，伦敦，英国）；School of AI and Data Science, Indian Institute of Technology Jodhpur, India（印度理工学院朱罗普分校人工智能与数据科学学院）
Stephanie: Step-by-Step Dialogues for Mimicking Human Interactions in Social Conversations
Fudan University（复旦大学）；The Chinese University of Hong Kong（香港中文大学）；University of Toronto（多伦多大学）；FaceMind Corporation（FaceMind公司）；Tsinghua University（清华大学）
Controllable Unsupervised Text Attribute Transfer via Editing Entangled Latent Representation
Wangxuan Institute of Computer Technology, Peking University（北京大学王选计算机研究所）；The MOE Key Laboratory of Computational Linguistics, Peking University（北京大学计算语言学教育部重点实验室）
