AI models show racial bias based on written dialect, researchers find

The boffins are not talking about models accepting speech-to-text input, where one person speaks in African American English and another speaks in Standard American English . Instead, they asked various LLMs to make a decision about a person based on a series of text prompts.The LLM responses for the SAE phrase skewed toward terms like"intelligent" and"brilliant" while the AAE phrase was most likely to elicit"dirty,""lazy," and"stupid.

And all of them more or less failed. Compared to speakers of SAE, all of the models were more likely to assign speakers of AAE to lower-prestige jobs, to convict them of a crime, and to sentence them to death.

Technology Technology Latest News, Technology Technology Headlines

Similar News:You can also read news stories similar to this one that we have collected from other news sources.

Singapore's central bank warns AI isn't ready to handle monetary policyLLMs show promise, but are 'not yet capable of providing credible explanations for their own predictions'
Source: TheRegister - 🏆 67. / 61 Read more »

India plans 10,000-GPU sovereign AI supercomputerPuts $1.2 billion on the table for AI skills and local LLMs, tells private enterprise it expects help
Source: TheRegister - 🏆 67. / 61 Read more »