for ML engineers: why can't you simply exclude the word "fuck"? (slrpnk.net)

submitted 11 months ago* (last edited 11 months ago) by FinallyDebunked@slrpnk.net to c/asklemmy@lemmy.world

16 comments fedilink hide all child comments

So, I've heard that ML manipulates tokens and specifically for the English corpora they take place of words. If we want model to be polite and not to speak uncomfortable language we can remove certain words from the internal array where all tokens and their associative data are stored, for example "fuck".

you are viewing a single comment's thread
view the rest of the comments

[-] BURN@lemmy.world 13 points 11 months ago

ML/Generative AI don’t “store” an internal array of specifics. Instead it’s a statistical model based on the next (or in ChatGPT’s case, 3rd most likely) word in a sentence.

To avoid swearing or other really anything it needs to be excluded at a training level, before the algorithm is trained.

As it stands, we have very little to no visibility into why these models work. Even the researchers are trying to open the black box, but there’s so much that it’s nearly impossible to isolate a node that would or would not contain the work fuck

[-] xerox@lemm.ee 2 points 11 months ago

(or in ChatGPT’s case, 3rd most likely)

Why 3rd?

[-] BURN@lemmy.world 9 points 11 months ago

I believe that the 3rd or nth, word is because it sounds more human. The statistically first correct word ends up sounding very robotic and forced, where the 3rd is still very likely correct, but leads to variation in responses

This is all from what I remember reading a mini-paper about it, so I could be wrong

load more comments (3 replies)

this post was submitted on 25 Sep 2023

22 points (82.4% liked)

Ask Lemmy

26208 readers

2562 users here now

A Fediverse community for open-ended, thought provoking questions

Rules: (interactive)

1) Be nice and; have fun

Doxxing, trolling, sealioning, racism, and toxicity are not welcomed in AskLemmy. Remember what your mother said: if you can't say something nice, don't say anything at all. In addition, the site-wide Lemmy.world terms of service also apply here. Please familiarize yourself with them

2) All posts must end with a '?'

This is sort of like Jeopardy. Please phrase all post titles in the form of a proper question ending with ?

3) No spam

Please do not flood the community with nonsense. Actual suspected spammers will be banned on site. No astroturfing.

4) NSFW is okay, within reason

Just remember to tag posts with either a content warning or a [NSFW] tag. Overtly sexual posts are not allowed, please direct them to either !asklemmyafterdark@lemmy.world or !asklemmynsfw@lemmynsfw.com. NSFW comments should be restricted to posts tagged [NSFW].

5) This is not a support community.

It is not a place for 'how do I?', type questions. If you have any questions regarding the site itself or would like to report a community, please direct them to Lemmy.world Support or email info@lemmy.world. For other questions check our partnered communities list, or use the search function.

Reminder: The terms of service apply here too.