Incorporating External Knowledge and Goal Guidance for LLM-based Conversational Recommender Systems

arXiv:2405.01868v1 Announce Type: new
Abstract: This paper aims to efficiently enable large language models (LLMs) to use external knowledge and goal guidance in conversational recommender system (CRS) tasks. Advanced LLMs (e.g., ChatGPT) are limited in domain-specific CRS tasks for 1) generating grounded responses with recommendation-oriented knowledge, or 2) proactively leading the conversations through different dialogue goals. In this work, we first analyze those limitations through a comprehensive evaluation, showing the necessity of external knowledge and goal guidance which contribute significantly …

abstract advanced arxiv chatgpt conversational cs.cl domain guidance knowledge language language models large language large language models llm llms paper recommendation recommender systems responses systems tasks type