Personalization in large language models (LLMs) is increasingly important, aiming to align LLM's interactions, content, and recommendations with individual user preferences. Recent advances in LLM personalization have spotlighted effective prompt design, by enriching user queries with non-parametric knowledge through behavior history retrieval and textual profiles. However, these approaches were limited due to a lack of model ownership, resulting in constrained customization and privacy issues. Moreover, they often failed to accurately capture user behavior patterns, especially in cases where user data were complex and dynamic. To address these shortcomings, we introduce One PEFT Per User (OPPU), which employs personalized parameter-efficient fine-tuning (PEFT) modules, to store user-specific behavior patterns and preferences. By plugging in users' personal PEFT parameters, they can own and use their LLMs personally. OPPU integrates parametric user knowledge in the personal PEFT parameters with the non-parametric knowledge acquired through retrieval and profile. This integration adapts individual LLMs to user behavior shifts. Experimental results demonstrate that OPPU significantly outperforms existing prompt-based methods across seven diverse tasks in the LaMP benchmark. Further in-depth studies reveal OPPU's enhanced capabilities in handling user behavior shifts, modeling users at different active levels, maintaining robustness across various user history formats, and displaying versatility with different PEFT methods.

翻译：大语言模型（LLMs）的个性化日益重要，旨在使其交互、内容生成及推荐与个体用户偏好对齐。近期LLM个性化研究聚焦于高效提示设计，通过行为历史检索和文本档案为用户查询注入非参数化知识。然而，这些方法因缺乏模型自主性而面临定制受限和隐私问题。此外，在用户数据复杂多变的情况下，它们往往难以准确捕捉用户行为模式。为克服上述局限，我们提出"每用户单PEFT"（OPPU）方法，采用个性化参数高效微调（PEFT）模块存储用户专属行为模式与偏好。通过接入用户的个性化PEFT参数，用户可自主拥有并使用其专属LLM。OPPU将个人PEFT参数中的参数化用户知识与通过检索和档案获得的非参数化知识相融合，使个体化LLM能适应行为变化。实验结果表明，在LaMP基准测试的七项不同任务中，OPPU显著优于现有基于提示的方法。进一步的深入研究揭示了OPPU在应对用户行为变化、建模不同活跃度用户、保持跨多种用户历史格式的鲁棒性，以及展现对不同PEFT方法的兼容性等方面的增强能力。