Re:Do Large Language Models learn world models or just surfa...
by bsk7 on Sunday January 22, 2023 @12:24PM
(#34479739)
> An inaccurate engine and a statistical one are indistinguishable.
How so? The paper is trying to assess if some semantic understanding is being created by the underlying model, not if a completely accurate one is. If such a world model maps to Othello-prime (gleaning concepts like tiles, colors etc), that is still a very interesting result.
An inaccurate engine and a statistical one are indistinguishable. And the authors provide no evidence to prefer the former.
Nothing is ruled out, of course, but there's not strong or compelling evidence either.