Tidying Up the Conversational Recommender Systems' Biases

TL;DR

This paper reviews biases in conversational recommender systems, highlighting the importance of a holistic approach to understanding and mitigating biases across system components and their integration.

Contribution

It provides a comprehensive survey of biases in CRS, including analysis of biases in individual components and their interactions within complex models.

Findings

Biases exist at multiple stages of CRS development.

Integrating language models can amplify existing biases.

A holistic approach is essential for bias mitigation.

Abstract

The growing popularity of language models has sparked interest in conversational recommender systems (CRS) within both industry and research circles. However, concerns regarding biases in these systems have emerged. While individual components of CRS have been subject to bias studies, a literature gap remains in understanding specific biases unique to CRS and how these biases may be amplified or reduced when integrated into complex CRS models. In this paper, we provide a concise review of biases in CRS by surveying recent literature. We examine the presence of biases throughout the system's pipeline and consider the challenges that arise from combining multiple models. Our study investigates biases in classic recommender systems and their relevance to CRS. Moreover, we address specific biases in CRS, considering variations with and without natural language understanding capabilities, along with biases related to dialogue systems and language models. Through our findings, we highlight the necessity of adopting a holistic perspective when dealing with biases in complex CRS models.