Measuring Gender and Racial Biases in Large Language Models

TL;DR

This study evaluates gender and racial biases in OpenAI's GPT when used for high-stakes resume screening, revealing biases that could impact fairness in AI-driven hiring decisions and highlighting the need for bias mitigation strategies.

Contribution

It provides a large-scale empirical analysis of social biases in GPT in a realistic decision-making scenario, identifying specific patterns and their potential impact on fairness.

Findings

GPT awards higher scores to female candidates with similar qualifications.

GPT scores lower for black male candidates with similar qualifications.

Biases could influence hiring probabilities by 1-2 percentage points.

Abstract

In traditional decision making processes, social biases of human decision makers can lead to unequal economic outcomes for underrepresented social groups, such as women, racial or ethnic minorities. Recently, the increasing popularity of Large language model based artificial intelligence suggests a potential transition from human to AI based decision making. How would this impact the distributional outcomes across social groups? Here we investigate the gender and racial biases of OpenAIs GPT, a widely used LLM, in a high stakes decision making setting, specifically assessing entry level job candidates from diverse social groups. Instructing GPT to score approximately 361000 resumes with randomized social identities, we find that the LLM awards higher assessment scores for female candidates with similar work experience, education, and skills, while lower scores for black male candidates with comparable qualifications. These biases may result in a 1 or 2 percentage point difference in hiring probabilities for otherwise similar candidates at a certain threshold and are consistent across various job positions and subsamples. Meanwhile, we also find stronger pro female and weaker anti black male patterns in democratic states. Our results demonstrate that this LLM based AI system has the potential to mitigate the gender bias, but it may not necessarily cure the racial bias. Further research is needed to comprehend the root causes of these outcomes and develop strategies to minimize the remaining biases in AI systems. As AI based decision making tools are increasingly employed across diverse domains, our findings underscore the necessity of understanding and addressing the potential unequal outcomes to ensure equitable outcomes across social groups.