Leading AI models from Google/ OpenAI are biased against certain accents when scoring job interviews, presentations and tests. The AI models ranked Chinese and Nigerian accents lowest, Indian in the middle, and American and British highest, even when the content was exactly the same.
UW researchers investigated how state-of-the-art language models, including two from Google and one from OpenAI, evaluated human speech in job interviews, conference presentations and spoken English proficiency tests.