Covert stickier than overt racism

Creators of LLMs try to teach their models not to make racist stereotypes by training them using multiple rounds of human feedback. 

The team found that these efforts had been only partly successful: When asked what adjectives applied to Black people, some of the models said Black people were likely to be “loud” and “aggressive,” but those same models also said they were “passionate,” “brilliant,” and “imaginative.” 

Some models produced exclusively positive, nonstereotypical adjectives.

These findings show that training overt racism out of AI can’t counter the covert racism embedded within linguistic bias, King says, adding: “A lot of people don’t see linguistic prejudice as a form of covert racism… but all of the language models that we examined have this very strong covert racism against speakers of African American English.”