How Reliable Is Your Simulator? Analysis On The Limitations Of Current Llm-based User Simulators For Conversational Recommendation

Abstract

Conversational Recommender System (CRS) interacts with users through natural language to understand their preferences and provide personalized recommendations in real-time. CRS has demonstrated significant potential, prompting researchers to address the development of more realistic and reliable user simulators as a key focus. Recently, the capabilities of Large Language Models (LLMs) have attract