Re:The unequal treatment of demographic groups by ChatGPT/Op...
by klipt on Thursday February 02, 2023 @03:55PM
(#34632853)
> about as unbiased as we're going to get.
You can easily force the model to be more unbiased. Just add a filter that flips the gender of words, evaluates the hate score for both the original and flipped version, and averages the results.
Guaranteed to give the same score regardless of the gender mentioned.
Re:The unequal treatment of demographic groups by ChatGPT/Op...
by ineptech on Thursday February 02, 2023 @04:58PM
(#34633784)
Clever idea, but I don't think this would work very well on real posts. Consider a model that rates "typical woman driver" as hateful, because that phrase appears in a lot of argument threads with lots of downvotes. Your approach would average its score with that of "typical man driver", which will presumably be very low, not because it's less hateful but because it just rarely shows up in the training corpus.
I don't think we as a society have an answer to that, so it's hardly fair to expect ChatGPT to provide one. What it currently does is produce similar-but-not-equal scores to sentences like those - maybe "I hate men" is 0.52 and "I hate women" is 0.73 - and if you filter out anything higher than 0.4 then they both get flagged, which seems about as unbiased as we're going to get.