Measuring What Makes You Unique: Difference-Aware User Modeling for Enhancing LLM Personalization

2025-03-04

AI Summary

Existing LLM personalization methods rely solely on modeling individual user histories, neglecting cross-user heterogeneity analysis and thus failing to identify key factors driving preference divergence. This paper proposes Difference-Aware Personalized Learning (DPL), the first framework to incorporate cross-user contrastive modeling into LLM personalization. DPL introduces a structured difference extraction criterion and a differentiable representative user selection mechanism to construct task-aware heterogeneous preference contexts. It further integrates contrastive user representation alignment, difference-aware knowledge distillation, and lightweight adapter fine-tuning. Evaluated on multiple real-world datasets, DPL achieves substantial improvements in generation quality (BLEU-4 +2.7) and personalization consistency (+18.3%), marking a paradigm shift from “individual induction” to “contrastive discrimination.” The code is publicly available.

Technology Category

• Machine Learning: Learning Preferences or Rankings
• Humans and AI: Learning Human Values and Preferences
• Natural Language Processing: (Large) Language Models

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Personalizing Large Language Models (LLMs) has become a critical step in facilitating their widespread application to enhance individual life experiences. In pursuit of personalization, distilling key preference information from an individual's historical data as instructional preference context to customize LLM generation has emerged as a promising direction. However, these methods face a fundamental limitation by overlooking the inter-user comparative analysis, which is essential for identifying the inter-user differences that truly shape preferences. To address this limitation, we propose Difference-aware Personalization Learning (DPL), a novel approach that emphasizes extracting inter-user differences to enhance LLM personalization. DPL strategically selects representative users for comparison and establishes a structured standard to extract meaningful, task-relevant differences for customizing LLM generation. Extensive experiments on real-world datasets demonstrate that DPL significantly enhances LLM personalization. We release our code at https://github.com/SnowCharmQ/DPL.

Problem

• Enhance LLM personalization by identifying inter-user differences.
• Extract meaningful, task-relevant differences for customizing LLM generation.
• Propose Difference-aware Personalization Learning (DPL) to improve personalization.

Innovation

• DPL emphasizes inter-user difference extraction
• Strategic selection of representative users for comparison
• Structured standard for task-relevant difference extraction