无需配对数据，用低秩适配实现指令模型风格迁移。
StyleAdaptedLM: Enhancing Instruction Following Models with Efficient Stylistic Transfer
- 用LoRA在非结构化文本上训练风格适配器，再融合到指令模型。
- 多数据集实验显示风格一致性提升，指令遵循能力不受损。
- 适合需要品牌化对话、个性化语音的企业应用。
将大语言模型适配至特定风格（如品牌语气或作者语调）对企事业单位沟通至关重要，但现有方法在缺乏指令-响应格式语料时难以兼顾风格特征与指令遵循。本文提出StyleAdaptedLM框架，利用低秩适配（LoRA）高效迁移风格特征：先在基础模型上用多样化非结构化风格语料训练LoRA适配器，再将其合并至独立的指令跟随模型。该方法无需成对数据，即可实现稳健的风格定制，同时保持任务性能。多数据集与多模型实验表明，风格一致性显著提升，且人类评估确认模型成功吸收品牌特定表达规范。StyleAdaptedLM为大模型风格个性化提供了一条高效路径。
原文摘要 · Abstract (English)
Adapting LLMs to specific stylistic characteristics, like brand voice or authorial tones, is crucial for enterprise communication but challenging to achieve from corpora which lacks instruction-response formatting without compromising instruction adherence. We introduce StyleAdaptedLM, a framework that efficiently transfers stylistic traits to instruction-following models using Low-Rank Adaptation (LoRA). LoRA adapters are first trained on a base model with diverse unstructured stylistic corpora, then merged with a separate instruction-following model. This enables robust stylistic customization without paired data or sacrificing task performance. Experiments across multiple datasets and models demonstrate improved stylistic consistency while preserving instruction adherence, with human evaluations confirming brand-specific convention uptake. StyleAdaptedLM offers an efficient path for stylistic personalization in LLMs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。