Training-Free Token-Level Steering for LLM Personalized Co-Writing

Wenhao Mao; Chengbin Hou; Weixiao Wang; Jialiang Zhu; Min Liu; Yibin Hao; Hairong Lv

Training-Free Token-Level Steering for LLM Personalized Co-Writing

Computation and Language 2026-08-06 v1

Authors: Wenhao Mao , Chengbin Hou , Weixiao Wang , Jialiang Zhu , Min Liu , Yibin Hao , Hairong Lv

Abstract

While Large Language Models (LLMs) show great promise for personalization, they often lack specialized domain knowledge. Conventional solutions like fine-tuning struggle with high computational costs and rapid data updates, while Retrieval-Augmented Generation fails to provide fine-grained, token-level steering. Furthermore, chat-based interfaces remain dominant, whereas productive co-writing paradigms have not yet been well exploited beyond the coding domain. To this end, we introduce SteerWrite, a training-free framework designed for personalized co-writing. Our method effectively adapts the base model to specialized domains without gradient updates, with specific designs tailored to small datasets. Experiments demonstrate that SteerWrite achieves state-of-the-art performance across diverse datasets, metrics, and models, significantly reducing human editing effort.

Keywords

large language models personalization co-writing training-free token-level steering retrieval-augmented generation

Cite

@article{arxiv.2608.06069,
  title  = {Training-Free Token-Level Steering for LLM Personalized Co-Writing},
  author = {Wenhao Mao and Chengbin Hou and Weixiao Wang and Jialiang Zhu and Min Liu and Yibin Hao and Hairong Lv},
  journal= {arXiv preprint arXiv:2608.06069},
  year   = {2026}
}