Measuring What Makes You Unique: Difference-Aware User Modeling for Enhancing LLM Personalization
This work addresses the challenge of improving LLM personalization for individual users, representing an incremental advancement by focusing on inter-user differences rather than introducing a new paradigm.
The paper tackles the problem of personalizing Large Language Models (LLMs) by addressing the limitation of existing methods that overlook inter-user comparative analysis, proposing Difference-aware Personalization Learning (DPL) to extract inter-user differences, which significantly enhances LLM personalization as demonstrated in experiments on real-world datasets.
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.