Gender and Race Bias in Consumer Product Recommendations by Large Language Models

TL;DR

This paper investigates how large language models generate consumer product recommendations that may contain gender and race biases, highlighting disparities across demographic groups and emphasizing the need for more equitable systems.

Contribution

It is among the first studies to analyze gender and race biases in LLM-generated recommendations using multiple analytical methods.

Findings

Significant disparities in recommendations for different demographic groups

Biases are quantifiable using Marked Words, SVM, and Jensen-Shannon methods

Highlighting the importance of addressing bias in LLM recommendation systems

Abstract

Large Language Models are increasingly employed in generating consumer product recommendations, yet their potential for embedding and amplifying gender and race biases remains underexplored. This paper serves as one of the first attempts to examine these biases within LLM-generated recommendations. We leverage prompt engineering to elicit product suggestions from LLMs for various race and gender groups and employ three analytical methods-Marked Words, Support Vector Machines, and Jensen-Shannon Divergence-to identify and quantify biases. Our findings reveal significant disparities in the recommendations for demographic groups, underscoring the need for more equitable LLM recommendation systems.