Unveiling Inference Scaling for Difference-Aware User Modeling in LLM Personalization

TL;DR

This paper introduces DRP, a novel framework that leverages inference scaling in LLMs to better capture user differences for improved personalization, combining quick and deliberate reasoning processes.

Contribution

It proposes a difference-aware reasoning framework that enhances user modeling by using inference scaling to identify and describe user differences more effectively.

Findings

DRP outperforms baseline methods in personalized review generation.

The framework effectively identifies relevant user difference features.

Structured descriptions improve the granularity of user modeling.

Abstract

Large Language Models (LLMs) are increasingly integrated into users' daily lives, driving a growing demand for personalized outputs. Prior work has primarily leveraged a user's own history, often overlooking inter-user differences that are critical for effective personalization. While recent methods have attempted to model such differences, their feature extraction processes typically rely on fixed dimensions and quick, intuitive inference (System-1 thinking), limiting both the coverage and granularity of captured user differences. To address these limitations, we propose Difference-aware Reasoning Personalization (DRP), a framework that reconstructs the difference extraction mechanism by leveraging inference scaling to enhance LLM personalization. DRP autonomously identifies relevant difference feature dimensions and generates structured definitions and descriptions, enabling slow, deliberate reasoning (System-2 thinking) over user differences. Experiments on personalized review generation demonstrate that DRP consistently outperforms baseline methods across multiple metrics.