AI generates covertly racist decisions about people based on their dialect

Abstract Hundreds of millions of people now interact with language models, with uses ranging from help with writing 1,2 to informing hiring decisions 3 . However, these language models are known to perpetuate systematic racial prejudices, making their judgements biased in problematic ways about groups such as African Americans 4–7 . 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 movement 8,9 . It is unknown whether this covert racism manifests in language models. Here, we demonstrate that language models embody covert racism in the…