Personalized LLMs can significantly enhance user experiences by tailoring responses to preferences such as helpfulness, conciseness, and humor. However, fine-tuning models to address all possible combinations of user preferences is computationally expensive and impractical. In this paper, we introduce \textbf{CLIPer}(\textbf{Cl}assifier-guided \textbf{I}nference-time \textbf{Per}sonalization), a lightweight personalization approach that leverages a classifier model to steer LLM generation dynamically to different user preferences at inference time. Our method eliminates the need for extensive fine-tuning, inducing negligible additional computational overhead while enabling more controllable and nuanced personalization across single and multi-dimensional preferences. Comprehensive empirical analyses demonstrate the scalability and effectiveness of our approach in delivering personalized language generation.
@article{arxiv.2605.07162,
title = {CLIPer: Tailoring Diverse User Preference via Classifier-Guided Inference-Time Personalization},
author = {Jinyan Su and Jinpeng Zhou and Claire Cardie and Wen Sun},
journal= {arXiv preprint arXiv:2605.07162},
year = {2026}
}