LLMs have a strong bias against use of African American English
Feedback gets rid of overt biases but leaves subtle racism intact.
You're viewing a single thread.
They can't possibly encounter much of it in training material... Of course they're not going to like it.
What?
It trains off social media, and even white kids use AAVE online. And kids make the most social media comments.
A lot of times when someone posts a text screenshot and everyone talks about how kids talk crazy, it's just a patois of AAEV mixed in with "regular" English.
It should be able to "read" it fine.
The bias part (as clearly stated in the article...) is when you ask a LLM to describe the person who would phrase something in AAVE, and the LLM replies back with stereotypes about Black people.
So it can read and interpret it fine, it just has a bias against people who talk like that
LLM’s don’t have a bias against anyone, it’s literally just data. And those models are by and large fed with traditionally grammatically correct data. They don’t understand dialects, you’re looking soooooo hard for something to be offended over
If you're going to revive a 3+ day old thread...
At least read the article first so you have a clue what other people were talking about
