LLMs produce racist output when prompted in African American English
LLMs produce racist output when prompted in African American English
Large language models exhibit racial prejudices on the basis of dialect.
You're viewing a single thread.
Although nonstandard English and pidgins often demonstrate the same level of nuance and complexity as standard English, it's very common for there to be negative stereotypes. One has to wonder whether the LLMs generated from (stolen en masse) written output say as much about us as they do about their creators.
Pretty much, it was trained on human writing, then people are all surprised when it has human biases.
An LLM needs to evaluate and modify the preliminary output before actually sending it. In the context of a human mind that’s called thinking before opening your mouth.
Who among us couldn't benefit from a little more of that?
Humans aren’t always very good at that, and LLMs were trained on stuff written by humans, so here we are.
Exciting new product from the tech industry: Fruit from the poisoned tree!