CURP: 基于码本的连续用户表示用于大语言模型的个性化生成
CURP: Codebook-based Continuous User Representation for Personalized Generation with LLMs
AI总结：
提出CURP框架，通过双向用户编码器和离散原型码本提取多维用户特征，实现少量可训练参数的即插即用个性化生成，在变体生成任务上优于强基线。
摘要：
用户建模通过个体的偏好和行为模式来表征用户，从而在当代方法中实现与大语言模型（LLMs）的个性化模拟和生成。然而，现有方法（无论是基于提示的方法还是基于训练的方法）在平衡个性化质量与计算和数据效率方面面临挑战。我们提出了一个新颖的框架CURP，它采用双向用户编码器和离散原型码本来提取多维用户特征。这种设计使得即插即用的个性化成为可能，且只需少量可训练参数（约2000万参数，约占模型总大小的0.2%）。通过在变体生成任务上的大量实验，我们表明CURP相比强基线实现了更优的性能和泛化能力，同时提供了更好的可解释性和可扩展性。代码可在https://github.com/RaidonWong/CURP_code获取。
英文摘要：
User modeling characterizes individuals through their preferences and behavioral patterns to enable personalized simulation and generation with Large Language Models (LLMs) in contemporary approaches. However, existing methods, whether prompt-based or training-based methods, face challenges in balancing personalization quality against computational and data efficiency. We propose a novel framework CURP, which employs a bidirectional user encoder and a discrete prototype codebook to extract multi-dimensional user traits. This design enables plug-and-play personalization with a small number of trainable parameters (about 20M parameters, about 0.2\% of the total model size). Through extensive experiments on variant generation tasks, we show that CURP achieves superior performance and generalization compared to strong baselines, while offering better interpretability and scalability. The code are available at https://github.com/RaidonWong/CURP_code
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
