ULMRec: User-centric Large Language Model for Sequential Recommendation

TL;DR

ULMRec is a novel framework that enhances large language models for sequential recommendation by integrating user preferences and item semantics, leading to improved personalization and recommendation accuracy.

Contribution

This paper introduces ULMRec, a new method that incorporates user-specific preferences into LLMs using user indexing and alignment tuning, addressing limitations of item-level focus in prior models.

Findings

ULMRec significantly outperforms existing recommendation methods on public datasets.

Replacing item IDs with titles enables better semantic understanding.

User indexing and alignment tuning improve personalization accuracy.

Abstract

Recent advances in Large Language Models (LLMs) have demonstrated promising performance in sequential recommendation tasks, leveraging their superior language understanding capabilities. However, existing LLM-based recommendation approaches predominantly focus on modeling item-level co-occurrence patterns while failing to adequately capture user-level personalized preferences. This is problematic since even users who display similar behavioral patterns (e.g., clicking or purchasing similar items) may have fundamentally different underlying interests. To alleviate this problem, in this paper, we propose ULMRec, a framework that effectively integrates user personalized preferences into LLMs for sequential recommendation. Considering there has the semantic gap between item IDs and LLMs, we replace item IDs with their corresponding titles in user historical behaviors, enabling the model to capture the item semantics. For integrating the user personalized preference, we design two key components: (1) user indexing: a personalized user indexing mechanism that leverages vector quantization on user reviews and user IDs to generate meaningful and unique user representations, and (2) alignment tuning: an alignment-based tuning stage that employs comprehensive preference alignment tasks to enhance the model's capability in capturing personalized information. Through this design, ULMRec achieves deep integration of language semantics with user personalized preferences, facilitating effective adaptation to recommendation. Extensive experiments on two public datasets demonstrate that ULMRec significantly outperforms existing methods, validating the effectiveness of our approach.