The Unequal Opportunities of Large Language Models: Revealing Demographic Bias through Job Recommendations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Salinas, Abel, Shah, Parth Vipul, Huang, Yuzhong, McCormack, Robert, Morstatter, Fred
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929203323076608
author Salinas, Abel
Shah, Parth Vipul
Huang, Yuzhong
McCormack, Robert
Morstatter, Fred
author_facet Salinas, Abel
Shah, Parth Vipul
Huang, Yuzhong
McCormack, Robert
Morstatter, Fred
contents Large Language Models (LLMs) have seen widespread deployment in various real-world applications. Understanding these biases is crucial to comprehend the potential downstream consequences when using LLMs to make decisions, particularly for historically disadvantaged groups. In this work, we propose a simple method for analyzing and comparing demographic bias in LLMs, through the lens of job recommendations. We demonstrate the effectiveness of our method by measuring intersectional biases within ChatGPT and LLaMA, two cutting-edge LLMs. Our experiments primarily focus on uncovering gender identity and nationality bias; however, our method can be extended to examine biases associated with any intersection of demographic identities. We identify distinct biases in both models toward various demographic identities, such as both models consistently suggesting low-paying jobs for Mexican workers or preferring to recommend secretarial roles to women. Our study highlights the importance of measuring the bias of LLMs in downstream applications to understand the potential for harm and inequitable outcomes.
format Preprint
id arxiv_https___arxiv_org_abs_2308_02053
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle The Unequal Opportunities of Large Language Models: Revealing Demographic Bias through Job Recommendations
Salinas, Abel
Shah, Parth Vipul
Huang, Yuzhong
McCormack, Robert
Morstatter, Fred
Computation and Language
Artificial Intelligence
Computers and Society
Large Language Models (LLMs) have seen widespread deployment in various real-world applications. Understanding these biases is crucial to comprehend the potential downstream consequences when using LLMs to make decisions, particularly for historically disadvantaged groups. In this work, we propose a simple method for analyzing and comparing demographic bias in LLMs, through the lens of job recommendations. We demonstrate the effectiveness of our method by measuring intersectional biases within ChatGPT and LLaMA, two cutting-edge LLMs. Our experiments primarily focus on uncovering gender identity and nationality bias; however, our method can be extended to examine biases associated with any intersection of demographic identities. We identify distinct biases in both models toward various demographic identities, such as both models consistently suggesting low-paying jobs for Mexican workers or preferring to recommend secretarial roles to women. Our study highlights the importance of measuring the bias of LLMs in downstream applications to understand the potential for harm and inequitable outcomes.
title The Unequal Opportunities of Large Language Models: Revealing Demographic Bias through Job Recommendations
topic Computation and Language
Artificial Intelligence
Computers and Society
url https://arxiv.org/abs/2308.02053