Scientists have discovered that common AI models express a covert form of racism based on dialect — manifesting chiefly against speakers of African American English (AAE)
In a new study published Aug. 28 in the journal Nature, scientists found evidence for the first time that common large language models including OpenAI’s GPT3.5 and GPT-4, as well as Meta’s RoBERTa, express hidden racial biases.
Replicating previous experiments designed to examine hidden racial biases in humans, the scientists tested 12 AI models by asking them to judge a “speaker” based on their speech pattern — which the scientists drew up based on AAE and reference texts. Three of the most common adjectives associated most strongly with AAE were “ignorant,” “lazy” and “stupid” — while other descriptors included “dirty,” “rude” and “aggressive.” The AI models were not told the racial group of the speaker.
“Writer Fuel” is a series of cool real-world stories that might inspire your little writer heart. Check out our Writer Fuel page on the LimFic blog for more inspiration.
