Re:GPTs and Hallucination
by not2b on Tuesday September 10, 2024 @12:44PM
(#41502793)
"Why would a language model do anything other than "hallucinate" (i.e. generate words without any care about truthiness) ?"
That's exactly the question the paper attempts to answer: why do LLMs ever get it right? The answer is that on topics where there's a lot of data and a general consensus on what the right answer is, the statistical model will find that answer, and otherwise you get junk. That's why they work so well for people trying to write Python or Javascript, for example.
But I already knew this, you might say. Sure, but the authors produced evidence to back it up.
Re:GPTs and Hallucination
by danielbln on Tuesday September 10, 2024 @02:40PM
(#41504119)
As context sizes grow, it's easier to add lots of information outside of training data via in-context learning, which should offset that issue quite a bit.
That's exactly the question the paper attempts to answer: why do LLMs ever get it right? The answer is that on topics where there's a lot of data and a general consensus on what the right answer is, the statistical model will find that answer, and otherwise you get junk. That's why they work so well for people trying to write Python or Javascript, for example.
But I already knew this, you might say. Sure, but the authors produced evidence to back it up.