Memory Assisted LLM for Personalized Recommendation System

TL;DR

This paper introduces MAP, a memory-assisted approach for personalized recommendations using LLMs, which dynamically incorporates user history to improve accuracy and adapt to growing user data.

Contribution

The paper proposes a novel Memory-Assisted Personalized LLM (MAP) that effectively captures and utilizes user history for enhanced personalized recommendations, outperforming existing prompt-based methods.

Findings

MAP outperforms regular LLM recommenders in experiments.

Performance advantage increases with larger user history.

Effective in both single domain and cross-domain scenarios.

Abstract

Large language models (LLMs) have demonstrated significant potential in solving recommendation tasks. With proven capabilities in understanding user preferences, LLM personalization has emerged as a critical area for providing tailored responses to individuals. Current studies explore personalization through prompt design and fine-tuning, paving the way for further research in personalized LLMs. However, existing approaches are either costly and inefficient in capturing diverse user preferences or fail to account for timely updates to user history. To address these gaps, we propose the Memory-Assisted Personalized LLM (MAP). Through user interactions, we first create a history profile for each user, capturing their preferences, such as ratings for historical items. During recommendation, we extract relevant memory based on similarity, which is then incorporated into the prompts to enhance personalized recommendations. In our experiments, we define a new task that enables testing with varying memory size under two scenarios: single domain where memory and tasks are from the same category and cross-domain (e.g. memory from movies and recommendation tasks in books). The results show that MAP outperforms regular LLM-based recommenders that integrate user history directly through prompt design. Moreover, as user history grows, MAP's advantage increases in both scenarios, making it more suitable for addressing successive personalized user requests.