LLM-based User Profile Management for Recommender System
Seunghwan Bang, Hwanjun Song
2025-02-21
Summary
This paper talks about PURE, a new system that uses advanced AI language models to make better product recommendations by learning from users' reviews and purchase history over time.
What's the problem?
Current recommendation systems mostly look at what people have bought before, but they don't pay much attention to the reviews people write. This means they're missing out on a lot of useful information about what users like and don't like.
What's the solution?
The researchers created PURE, which has three main parts: one that reads reviews and figures out what users care about, another that keeps updating what it knows about each user, and a third that uses all this information to suggest products. PURE keeps learning as users write new reviews, so it can change its recommendations as people's tastes change.
Why it matters?
This matters because it could make online shopping experiences much better. By understanding not just what people buy, but also what they say about their purchases, PURE can make smarter, more personalized recommendations. This could help people find products they'll really like, even as their preferences change over time, and it could help businesses better understand and serve their customers.
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.