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.
I'm not from USA, black, nor a native English speaker, but due to Linguistics I can give you guys some further info.
AAE (Afro-American English), in a nutshell, is a group of English varieties used by some speakers from USA and Canada. In a lot of aspects they resemble geographical varieties, like the ones you'd see in plenty other languages, but there's a key difference: it isn't used by people "of a certain region", but rather by people "of a certain race" (black people).
This is mostly but not completely spoken (cue to the term AAVE - the "V" stands for "vernacular"); it affects also the way that those people use the written language. So often you see AAE features in written English, like:
What the article is saying is that LLMs are biased against those features. It's a rather strong bias, and not noticed for a geographical variety used as reference (Appalachian English). In other words: the LLM has been fed racist babble, and now it's regurgitating it.
I see, that's very different from most countries I imagine? People often speak on their own local dialect, here a northeastern would informally speak a completely different portuguese than someone from the south, doesn't matter the race.
Yup, it's atypical even in the rest of the Americas. I think that the nearest equivalent in Portuguese would be the quilombola dialects, but even then it's way off - because those dialects are still geographically associated with their respective quilombos, not just with race.
Since they’re vernacular you’ll mostly hear them being spoken, they aren’t really written
AAVE is commonly "written" now because most writing is texts and social media comments. So even if they luck out and learn "proper" English, people still going to type on their phones the same way they talk.
Even for white kids, most of Gen Z slang is just taken from AAVE, when older people complaining about not being able to read zoomer slang from text or comments, it's just heavily influenced by AAVE.
There's been bleed over for centuries, but with the Internet and social media it's merging faster, which is common for dialects of people that interact frequently
Warning: I've edited the comment that you're replying to. I'm saying this for the sake of transparency, as you're clearly quoting the earlier version.
The key here is that AAVE is not written, but AAE is. That "V" is for vernacular, it excludes written English by definition.
Now, I'm not sure if those white kids are using AAE or simply borrowing things from AAE into their written English. I simply don't have data on that.
There’s been bleed over for centuries, but with the Internet and social media it’s merging faster, which is common for dialects of people that interact frequently
Varieties merging or splitting is rarely the result of just more contact between people; it's all about identity. If things are happening as you described them, it's simply that those white kids stopped seeing black people as "the others", to see them as "part of the same group as us".
That “V” is for vernacular, it excludes written English by definition.
Yeah. But most people "write" online like they speak...
https://commonwealthtimes.org/2021/02/18/aave-is-not-your-internet-slang-it-is-black-culture/
If people followed rules about language, yeah, vernacular would just be spoken speech. But that's not how it works. The rules are made to reflect what people are doing. The rules don't control what people do.
So yes, while the word vernacular commonly meant only spoken words, there ain't nothing stopping nobody from typing like they speak.
And people been doing it for a long time
Yeah. But most people “write” online like they speak…
That's a common misconception.
While your written and spoken varieties do interact a fair bit, no, people don't "write like they speak". Not even online.
And that is not simply an "ackshyually". A lot of AAVE features simply don't transpose into writing - like prosody, non-rhoticity, /ɪ/-breaking, /äɪ/-monophtongisation... at most you can consciously approximate them into writing, but they won't be there.
If people followed rules about language, yeah, vernacular would just be spoken speech. But that’s not how it works. The rules are made to reflect what people are doing.
That is not about people following/not following "rules", it's about nomenclature - it's exactly the reason why "AAE" and "AAVE" are necessary as separated terms.
at most you can consciously approximate them into writing, but they won’t be there.
....
A lot of the difficulty older white people have with it, is it's spelled phonetically to maintain those things.
I gave you a link, lots of people have talked about this, it's not just some idea I came up with.
You're still talking like language has to follow the rules.
That's backwards. The rules change to follow the language
Ain't you old enough to have heard "ain't ain't a word because it ain't in the dictionary"?
Well, now it is.
And now the dictionary lists "figuratively" as one of the definitions for "literally".
Insist on following rules, and the dictionary wouldn't update.
I don't know how to put it anymore plainly, I'm sorry if you still don't understand
You’re still talking like language has to follow the rules.
That is clearly false. Refer to what I said in the very comment that you're replying to: "That is not about people following/not following “rules”, it’s about nomenclature"
Please stop misrepresenting what I said.
I gave you a link, lots of people have talked about this, it’s not just some idea I came up with.
You're implying that I claimed that you came up with this. I did not.
The link does not contradict what I said. It's simply using a different nomenclature, using the acronym "AAVE" to the whole instead of strictly the vernacular varieties.
The informative content there (i.e. beyond definitions) is mostly accurate, but contrariwise to what you're implying, I am not contradicting it.
I don’t know how to put it anymore plainly, I’m sorry if you still don’t understand
Emphasis mine. Drop off the passive aggressiveness; the one here not understanding shit is you, as shown by the fact that you're consistently distorting what I said.
I'm not bothering further with you. Go put words on someone else's mouth.
