Rethinking the Evaluation for Conversational Recommendation in the Era of Large Language Models
Submission Type: Regular Long Paper
Submission Track: Dialogue and Interactive Systems
Keywords: Conversational Recommendation, Large Language Model, Evaluation
Abstract: The recent success of large language models (LLMs) has shown great potential to develop more powerful conversational recommender systems (CRSs), which rely on natural language conversations to satisfy user needs. In this paper, we embark on an investigation into the utilization of ChatGPT for CRSs, revealing the inadequacy of the existing evaluation protocol. It might overemphasize the matching with ground-truth items annotated by humans while neglecting the interactive nature of CRSs.
To overcome the limitation, we further propose an **i**nteractive **Eva**luation approach based on **L**L**M**s, named **iEvaLM**, which harnesses LLM-based user simulators. Our evaluation approach can simulate various system-user interaction scenarios. Through the experiments on two public CRS datasets, we demonstrate notable improvements compared to the prevailing evaluation protocol. Furthermore, we emphasize the evaluation of explainability, and ChatGPT showcases persuasive explanation generation for its recommendations. Our study contributes to a deeper comprehension of the untapped potential of LLMs for CRSs and provides a more flexible and realistic evaluation approach for future research about LLM-based CRSs.
Submission Number: 2578
Loading