LLM-Powered User Simulator for Recommender System

TL;DR

This paper presents an LLM-powered user simulator that explicitly models user preferences and behaviors, improving the training and evaluation of reinforcement learning-based recommender systems with high-fidelity data.

Contribution

It introduces a novel LLM-based user simulator combining logical and statistical models to better emulate real user engagement in recommendation systems.

Findings

High-fidelity simulation data improves recommender system training.

Effective across multiple datasets and recommendation scenarios.

Enhances the reliability and stability of user behavior simulation.

Abstract

User simulators can rapidly generate a large volume of timely user behavior data, providing a testing platform for reinforcement learning-based recommender systems, thus accelerating their iteration and optimization. However, prevalent user simulators generally suffer from significant limitations, including the opacity of user preference modeling and the incapability of evaluating simulation accuracy. In this paper, we introduce an LLM-powered user simulator to simulate user engagement with items in an explicit manner, thereby enhancing the efficiency and effectiveness of reinforcement learning-based recommender systems training. Specifically, we identify the explicit logic of user preferences, leverage LLMs to analyze item characteristics and distill user sentiments, and design a logical model to imitate real human engagement. By integrating a statistical model, we further enhance the reliability of the simulation, proposing an ensemble model that synergizes logical and statistical insights for user interaction simulations. Capitalizing on the extensive knowledge and semantic generation capabilities of LLMs, our user simulator faithfully emulates user behaviors and preferences, yielding high-fidelity training data that enrich the training of recommendation algorithms. We establish quantifying and qualifying experiments on five datasets to validate the simulator's effectiveness and stability across various recommendation scenarios.