LLM-based User Profile Management for Recommender System

arXiv cs.CL / 5/1/2026

💬 OpinionIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper argues that recommender systems can improve beyond purchase history by incorporating user-generated text such as reviews and product descriptions into LLM-driven recommendations.
It introduces PURE, an LLM-based framework that builds and continuously updates evolving user profiles using extracted preferences and product-feature summaries from reviews.
PURE is implemented via three components: a Review Extractor, a Profile Updater, and a Recommender that uses the latest profile to generate personalized suggestions.
The authors propose a continuous sequential recommendation evaluation setting that simulates real-world behavior by adding reviews over time and updating predictions incrementally.
Experiments on Amazon datasets show PURE outperforms prior LLM-based approaches by leveraging long-term user information while staying within token limits.

Abstract

The rapid advancement of Large Language Models (LLMs) has opened new opportunities in recommender systems by enabling zero-shot recommendation without conventional training. Despite their potential, most existing works rely solely on users' purchase histories, leaving significant room for improvement by incorporating user-generated textual data, such as reviews and product descriptions. Addressing this gap, we propose PURE, a novel LLM-based recommendation framework that builds and maintains evolving user profiles by systematically extracting and summarizing key information from user reviews. PURE consists of three core components: a Review Extractor for identifying user preferences and key product features, a Profile Updater for refining and updating user profiles, and a Recommender for generating personalized recommendations using the most current profile. To evaluate PURE, we introduce a continuous sequential recommendation task that reflects real-world scenarios by adding reviews over time and updating predictions incrementally. Our experimental results on Amazon datasets demonstrate that PURE outperforms existing LLM-based methods, effectively leveraging long-term user information while managing token limitations.