Communications of the ACM
AI Favors White Men Under 40
Said UCPH's Anders Sgaard, "Whereas White men under the age of 40 with shorter educations are the group that language models align best with, the worst alignment is with language used by young, non-White men."
Credit: NordWood Themes/Unsplash
"Insert the missing word: I closed the door to my ____." It's an exercise that many remember from their school days. Whereas some societal groups might fill in the space with the word "holiday home," others may be more likely to insert "dorm room" or "garage." To a large extent, our word choice depends on our age, where we are from in a country, and our social and cultural background.
However, the language models we put to use in our daily lives while using search engines, machine translation, engaging with chatbots and commanding Siri, speak the language of some groups better than others. This has been demonstrated by a study from the University of Copenhagen (UCPH) Department of Computer Science, which for the first time has studied whether language models favour the linguistic preferences of some demographic groups over others—referred to in the jargon as sociolectal biases. The answer? Yes.
"Across language models, we are able to observe systematic bias. Whereas White men under the age of 40 with shorter educations are the group that language models align best with, the worst alignment is with language used by young, non-White men," says Anders Søgaard, a professor at UCPH's Department of Computer Science and the lead author of the study.
From University of Copenhagen
View Full Article
No entries found