通过对比用户差异提升大模型个性化生成效果
Measuring What Makes You Unique: Difference-Aware User Modeling for Enhancing LLM Personalization
- 基于用户间差异构建个性化指令上下文
- 在真实数据集上显著提升个性化表现
- 适合需要精准用户建模的场景
个性化大语言模型已成为提升个体生活体验的关键步骤。当前方法通常从用户历史数据中提炼偏好信息作为指令上下文来定制生成内容，但普遍存在忽视用户间比较分析的问题，难以捕捉真正塑造偏好的差异特征。为此，本文提出差异感知个性化学习（DPL），通过选取代表性用户进行对比，建立结构化标准以提取任务相关、有意义的用户间差异，用于优化大模型生成。在真实数据集上的大量实验表明，DPL能显著增强个性化效果。代码已开源：https://github.com/SnowCharmQ/DPL。
原文摘要 · Abstract (English)
Personalizing Large Language Models (LLMs) has become a critical step in facilitating their widespread application to enhance individual life experiences. In pursuit of personalization, distilling key preference information from an individual's historical data as instructional preference context to customize LLM generation has emerged as a promising direction. However, these methods face a fundamental limitation by overlooking the inter-user comparative analysis, which is essential for identifying the inter-user differences that truly shape preferences. To address this limitation, we propose Difference-aware Personalization Learning (DPL), a novel approach that emphasizes extracting inter-user differences to enhance LLM personalization. DPL strategically selects representative users for comparison and establishes a structured standard to extract meaningful, task-relevant differences for customizing LLM generation. Extensive experiments on real-world datasets demonstrate that DPL significantly enhances LLM personalization. We release our code at https://github.com/SnowCharmQ/DPL.
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。