大语言模型（LLMs）中的个性化日益重要，其目标是使LLMs的交互、内容和推荐与个体用户偏好保持一致。近期进展突显了有效的提示设计，即通过行为历史检索和文本画像用非参数知识丰富用户查询。然而，这些方法因缺乏模型所有权而面临局限性，导致定制受限和隐私问题，并且往往无法捕捉复杂、动态的用户行为模式。为解决这些不足，我们提出One PEFT Per User（OPPU），采用个性化参数高效微调（PEFT）模块来存储用户特定的行为模式和偏好。通过插入个人PEFT参数，用户可以单独拥有并使用自己的LLMs。OPPU将个人PEFT参数中的参数化用户知识与来自检索和画像的非参数知识相整合，使LLMs适应用户行为变化。实验结果表明，OPPU在LaMP基准的七个多样化任务上显著优于现有的基于提示的方法。进一步研究揭示了OPPU在以下方面的增强能力：处理用户行为变化、对不同活跃水平的用户进行建模、在各种用户历史格式下保持鲁棒性，以及在不同PEFT方法中展现通用性。
英文摘要：
Personalization in large language models (LLMs) is increasingly important, aiming to align the LLMs' interactions, content, and recommendations with individual user preferences. Recent advances have highlighted effective prompt design by enriching user queries with non-parametric knowledge through behavior history retrieval and textual profiles. However, these methods faced limitations due to a lack of model ownership, resulting in constrained customization and privacy issues, and often failed to capture complex, dynamic user behavior patterns. To address these shortcomings, we introduce One PEFT Per User (OPPU), employing personalized parameter-efficient fine-tuning (PEFT) modules to store user-specific behavior patterns and preferences. By plugging in personal PEFT parameters, users can own and use their LLMs individually. OPPU integrates parametric user knowledge in the personal PEFT parameters with non-parametric knowledge from retrieval and profiles, adapting 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 studies reveal OPPU's enhanced capabilities in handling user behavior shifts, modeling users at different activity levels, maintaining robustness across various user history formats, and displaying versatility with different PEFT methods.
Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学人工智能学院 Gallagher 学院）；Engineering Research Center of Next-Generation Intelligent Search and Recommendation, MOE（下一代智能搜索与推荐工程研究中心，教育部）；Baidu Inc.（百度公司）
Discrete Prompt Tuning via Recursive Utilization of Black-box Multimodal Large Language Model for Personalized Visual Emotion Recognition
Graduate School of Information Science（信息科学研究生学校）；Technology, Hokkaido University, Sapporo 060-0814, Japan（技术，北海道大学，札幌060-0814，日本）；Office of Institutional Research, Hokkaido University, Sapporo 060-0808, Japan（机构研究办公室，北海道大学，札幌060-0808，日本）；Faculty of Information Science（信息科学学院）
PEToolLLM: Towards Personalized Tool Learning in Large Language Models
The Hong Kong Polytechnic University（香港理工大学）；National University of Singapore（新加坡国立大学）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）
Generate, Not Recommend: Personalized Multimodal Content Generation
School of Computer Science, Carnegie Mellon University（卡内基梅隆大学计算机科学系）；Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学agate智能学院）；Serendipity One Inc.（Serendipity One公司）
RecGPT: Generative Personalized Prompts for Sequential Recommendation via ChatGPT Training Paradigm
Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学高瓴人工智能学院）；Peking University（北京大学）；Kuaishou Technology（快手科技）；Unaffliated（无所属机构）
Large Language Models Empowered Personalized Web Agents
National University of Singapore（新加坡国立大学）；The Hong Kong Polytechnic University（香港理工大学）；University of Science and Technology of China（中国科学技术大学）；Eastern Institute of Technology（宁波东方理工大学）
