LLMs become more covertly racist with human intervention
[ad_1] Even when the two sentences had the same meaning, the models were more likely to apply adjectives like “dirty,” “lazy,” and “stupid” to speakers of AAE than speakers of Standard American English (SAE). The models associated speakers of AAE with less prestigious jobs (or didn’t associate them with having a job at all), and …
LLMs become more covertly racist with human intervention Read More »