Reducing Racial and Ethnic Bias in AI Models
Principal Investigator(s): View help for Principal Investigator(s) Tavishi Choudhary, Greenwich High; Tavishi Choudhary, Greenwich High
Version: View help for Version V1
| Name | File Type | Size | Last Modified |
|---|---|---|---|
|
|
application/vnd.openxmlformats-officedocument.spreadsheetml.sheet | 82.4 KB | 06/11/2024 05:05:PM |
Project Citation:
Choudhary, Tavishi, and Choudhary, Tavishi. Reducing Racial and Ethnic Bias in AI Models. Ann Arbor, MI: Inter-university Consortium for Political and Social Research [distributor], 2024-06-11. https://doi.org/10.3886/E205241V1
Project Description
Summary:
View help for Summary
Reducing Racial and Ethnic Bias in AI Models - 53% of adults in the US acknowledge racial bias as a significant issue, 23% of Asian adults experience cultural and ethnic bias, and more than 60% conceal their cultural heritage after racial abuse.This paper addresses the issue of racial bias in AI models using scientific, evidence-based analysis and auditing processes to identify biased responses from AI models and develop a mitigation tool.The methodology involves creating a comprehensive database of racially biased questions, terms, and phrases from thousands of legal cases, Wikipedia, and surveys, and then testing them on AI Models and analyzing the responses through sentiment analysis and human evaluation, and eventually creation of an 'AI-BiasAudit,' tool having a racial-ethnic database for social science researchers and AI developers to identify and prevent racial bias in AI models
Scope of Project
Subject Terms:
View help for Subject Terms
Reducing Racial and Ethnic Bias in AI Models
Related Publications
Published Versions
Report a Problem
Found a serious problem with the data, such as disclosure risk or copyrighted content? Let us know.
This material is distributed exactly as it arrived from the data depositor. ICPSR has not checked or processed this material. Users should consult the investigator(s) if further information is desired.