Fairness of ChatGPT

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Yunqi, Zhang, Lanjing, Zhang, Yongfeng
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917657565986816
author Li, Yunqi
Zhang, Lanjing
Zhang, Yongfeng
author_facet Li, Yunqi
Zhang, Lanjing
Zhang, Yongfeng
contents Understanding and addressing unfairness in LLMs are crucial for responsible AI deployment. However, there is a limited number of quantitative analyses and in-depth studies regarding fairness evaluations in LLMs, especially when applying LLMs to high-stakes fields. This work aims to fill this gap by providing a systematic evaluation of the effectiveness and fairness of LLMs using ChatGPT as a study case. We focus on assessing ChatGPT's performance in high-takes fields including education, criminology, finance and healthcare. To conduct a thorough evaluation, we consider both group fairness and individual fairness metrics. We also observe the disparities in ChatGPT's outputs under a set of biased or unbiased prompts. This work contributes to a deeper understanding of LLMs' fairness performance, facilitates bias mitigation and fosters the development of responsible AI systems.
format Preprint
id arxiv_https___arxiv_org_abs_2305_18569
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Fairness of ChatGPT
Li, Yunqi
Zhang, Lanjing
Zhang, Yongfeng
Machine Learning
Artificial Intelligence
Computation and Language
Computers and Society
Understanding and addressing unfairness in LLMs are crucial for responsible AI deployment. However, there is a limited number of quantitative analyses and in-depth studies regarding fairness evaluations in LLMs, especially when applying LLMs to high-stakes fields. This work aims to fill this gap by providing a systematic evaluation of the effectiveness and fairness of LLMs using ChatGPT as a study case. We focus on assessing ChatGPT's performance in high-takes fields including education, criminology, finance and healthcare. To conduct a thorough evaluation, we consider both group fairness and individual fairness metrics. We also observe the disparities in ChatGPT's outputs under a set of biased or unbiased prompts. This work contributes to a deeper understanding of LLMs' fairness performance, facilitates bias mitigation and fosters the development of responsible AI systems.
title Fairness of ChatGPT
topic Machine Learning
Artificial Intelligence
Computation and Language
Computers and Society
url https://arxiv.org/abs/2305.18569