"You Gotta be a Doctor, Lin": An Investigation of Name-Based Bias of Large Language Models in Employment Recommendations

TL;DR

This study investigates racial and gender biases in large language models by simulating hiring and salary decisions, revealing preferential treatment for White female-sounding names and salary disparities across demographics.

Contribution

It provides empirical evidence of name-based biases in LLMs and compares these biases with real-world labor market data, highlighting potential risks.

Findings

Models prefer White female-sounding names for hiring.

Salary recommendations vary by up to 5% across demographic groups.

Inconsistent alignment with U.S. labor market data.

Abstract

Social science research has shown that candidates with names indicative of certain races or genders often face discrimination in employment practices. Similarly, Large Language Models (LLMs) have demonstrated racial and gender biases in various applications. In this study, we utilize GPT-3.5-Turbo and Llama 3-70B-Instruct to simulate hiring decisions and salary recommendations for candidates with 320 first names that strongly signal their race and gender, across over 750,000 prompts. Our empirical results indicate a preference among these models for hiring candidates with White female-sounding names over other demographic groups across 40 occupations. Additionally, even among candidates with identical qualifications, salary recommendations vary by as much as 5% between different subgroups. A comparison with real-world labor data reveals inconsistent alignment with U.S. labor market characteristics, underscoring the necessity of risk investigation of LLM-powered systems.