this post was submitted on 01 Feb 2024
220 points (93.3% liked)
Technology
60105 readers
1855 users here now
This is a most excellent place for technology news and articles.
Our Rules
- Follow the lemmy.world rules.
- Only tech related content.
- Be excellent to each another!
- Mod approved content bots can post up to 10 articles per day.
- Threads asking for personal tech support may be deleted.
- Politics threads may be removed.
- No memes allowed as posts, OK to post as comments.
- Only approved bots from the list below, to ask if your bot can be added please contact us.
- Check for duplicates before posting, duplicates may be removed
Approved Bots
founded 2 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
This partly true especially models that deployed on public and uses large samples gathered from large amount of peoples. Now the parts that we can't control is if the model is trained with skewed dataset that benefits certain outcomes.
It depends on which stage of training. As the recent Anthropic research showed, fine tuning out behavior isn't so easy.
And at the pretrained layer you really can't get any halfway decent results with limited data sets, so you'd only be able to try to bias it at the fine tuned layer with biased sourcing, but then per the Anthropic findings (and the real world cases I mentioned above) you are only biasing a thin veneer over the pretrained layer.