CURP: Codebook-based Continuous User Representation for Personalized Generation with LLMs
For researchers and practitioners needing efficient, interpretable user modeling for LLM personalization, CURP offers a scalable solution that balances quality and computational cost.
CURP introduces a plug-and-play user representation framework using a bidirectional encoder and discrete codebook, achieving superior personalization in LLM generation with only 20M trainable parameters (0.2% of model size) and outperforming strong baselines.
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