Concept -- An Evaluation Protocol on Conversational Recommender Systems with System-centric and User-centric Factors

TL;DR

This paper introduces Concept, a comprehensive evaluation protocol for conversational recommender systems that considers both system effectiveness and user experience, using a large language model-based simulator.

Contribution

It proposes an inclusive evaluation framework that integrates system-centric and user-centric factors, with a detailed ability-based assessment using LLMs.

Findings

Identifies limitations of existing CRS evaluation methods.

Provides a balanced assessment of CRS performance and usability.

Highlights areas for improvement in current CRS models.

Abstract

The conversational recommendation system (CRS) has been criticized regarding its user experience in real-world scenarios, despite recent significant progress achieved in academia. Existing evaluation protocols for CRS may prioritize system-centric factors such as effectiveness and fluency in conversation while neglecting user-centric aspects. Thus, we propose a new and inclusive evaluation protocol, Concept, which integrates both system- and user-centric factors. We conceptualise three key characteristics in representing such factors and further divide them into six primary abilities. To implement Concept, we adopt a LLM-based user simulator and evaluator with scoring rubrics that are tailored for each primary ability. Our protocol, Concept, serves a dual purpose. First, it provides an overview of the pros and cons in current CRS models. Second, it pinpoints the problem of low usability in the "omnipotent" ChatGPT and offers a comprehensive reference guide for evaluating CRS, thereby setting the foundation for CRS improvement.