AI generates covertly racist decisions about people based on their dialect

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3AE9XNTWPC" target="_blank" >RIV/00216208:11320/25:E9XNTWPC - isvavai.cz</a>

Result on the web

<a href="https://www.scopus.com/inward/record.uri?eid=2-s2.0-85202506726&doi=10.1038%2fs41586-024-07856-5&partnerID=40&md5=82cfa7237f4d8030765c93eaf3050d1b" target="_blank" >https://www.scopus.com/inward/record.uri?eid=2-s2.0-85202506726&doi=10.1038%2fs41586-024-07856-5&partnerID=40&md5=82cfa7237f4d8030765c93eaf3050d1b</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1038/s41586-024-07856-5" target="_blank" >10.1038/s41586-024-07856-5</a>

Result language

angličtina

Original language name

AI generates covertly racist decisions about people based on their dialect

Original language description

Hundreds of millions of people now interact with language models, with uses ranging from help with writing1,2 to informing hiring decisions3. However, these language models are known to perpetuate systematic racial prejudices, making their judgements biased in problematic ways about groups such as African Americans4–7. Although previous research has focused on overt racism in language models, social scientists have argued that racism with a more subtle character has developed over time, particularly in the United States after the civil rights movement8,9. It is unknown whether this covert racism manifests in language models. Here, we demonstrate that language models embody covert racism in the form of dialect prejudice, exhibiting raciolinguistic stereotypes about speakers of African American English (AAE) that are more negative than any human stereotypes about African Americans ever experimentally recorded. By contrast, the language models’ overt stereotypes about African Americans are more positive. Dialect prejudice has the potential for harmful consequences: language models are more likely to suggest that speakers of AAE be assigned less-prestigious jobs, be convicted of crimes and be sentenced to death. Finally, we show that current practices of alleviating racial bias in language models, such as human preference alignment, exacerbate the discrepancy between covert and overt stereotypes, by superficially obscuring the racism that language models maintain on a deeper level. Our findings have far-reaching implications for the fair and safe use of language technology. © The Author(s) 2024.

Czech name

—

Czech description

—

Type

J_SC - Article in a specialist periodical, which is included in the SCOPUS database

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

—

Continuities

—

Publication year

2024

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Name of the periodical

Nature

ISSN

0028-0836

e-ISSN

—

Volume of the periodical

633

Issue of the periodical within the volume

8028

Country of publishing house

US - UNITED STATES

Number of pages

8

Pages from-to

147-154

UT code for WoS article

—

EID of the result in the Scopus database

2-s2.0-85202506726