Latent Inter-User Difference Modeling for LLM Personalization

TL;DR

This paper introduces DEP, a novel framework for LLM personalization that models inter-user differences in latent space, improving personalized review generation without relying on language prompts.

Contribution

DEP is the first approach to model inter-user differences in latent space using contrastive embeddings and autoencoders, enhancing personalization effectiveness.

Findings

DEP outperforms baseline methods on review generation metrics

Latent difference modeling improves personalization quality

Autoencoder filtering preserves task-relevant features

Abstract

Large language models (LLMs) are increasingly integrated into users' daily lives, leading to a growing demand for personalized outputs. Previous work focuses on leveraging a user's own history, overlooking inter-user differences that are crucial for effective personalization. While recent work has attempted to model such differences, the reliance on language-based prompts often hampers the effective extraction of meaningful distinctions. To address these issues, we propose Difference-aware Embedding-based Personalization (DEP), a framework that models inter-user differences in the latent space instead of relying on language prompts. DEP constructs soft prompts by contrasting a user's embedding with those of peers who engaged with similar content, highlighting relative behavioral signals. A sparse autoencoder then filters and compresses both user-specific and difference-aware embeddings, preserving only task-relevant features before injecting them into a frozen LLM. Experiments on personalized review generation show that DEP consistently outperforms baseline methods across multiple metrics. Our code is available at https://github.com/SnowCharmQ/DEP.