Investigating Gender and Racial Biases in DALL-E Mini Images

Author:

Cheong Marc1ORCID,Abedin Ehsan2ORCID,Ferreira Marinus3ORCID,Reimann Ritsaart3ORCID,Chalson Shalom4ORCID,Robinson Pamela4ORCID,Byrne Joanne1ORCID,Ruppanner Leah1ORCID,Alfano Mark3ORCID,Klein Colin4ORCID

Affiliation:

1. The University of Melbourne, Parkville, Australia

2. Flinders University, Adelaide, Australia and The University of Melbourne, Parkville, Australia

3. Macquarie University, Macquarie Park, Australia

4. Australian National University, Canberra, Australia

Abstract

Generative artificial intelligence systems based on transformers, including both text generators such as GPT-4 and image generators such as DALL-E 3, have recently entered the popular consciousness. These tools, while impressive, are liable to reproduce, exacerbate, and reinforce extant human social biases, such as gender and racial biases. In this article, we systematically review the extent to which DALL-E Mini suffers from this problem. In line with the Model Card published alongside DALL-E Mini by its creators, we find that the images it produces tend to represent dozens of different occupations as populated either solely by men (e.g., pilot, builder, plumber) or solely by women (e.g., hairdresser, receptionist, dietitian). In addition, the images DALL-E Mini produces tend to represent most occupations as populated primarily or solely by White people (e.g., farmer, painter, prison officer, software engineer) and very few by non-White people (e.g., pastor, rapper). These findings suggest that exciting new AI technologies should be critically scrutinized and perhaps regulated before they are unleashed on society.

Publisher

Association for Computing Machinery (ACM)

Reference80 articles.

1. Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI)

2. For minorities, biased AI algorithms can damage almost every part of life;The Conversation,2023

3. Esther Ajao. 2023. Reasons for and Effects of Microsoft Cutting AI Ethics Unit. Retrieved March 20 2023 from https://www.techtarget.com/searchenterpriseai/news/365532615/Reasons-for-and-effects-of-Microsoft-cutting-AI-ethics-unit

4. I. Ajunwa S. A. Friedler C. Scheidegger and S. Venkatasubramanian. 2016. Hiring by Algorithm: Predicting and Preventing Disparate Impact. Retrieved 12 DEC 2023 from http://sorelle.friedler.net/papers/SSRN-id2746078.pdf

5. Do Google’s ‘unprofessional hair’ results show it is racist?;Alexander Leigh;Guardian,2016

Cited by 4 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3