It has probably seen the correct nouns used millions of times in the training data - and asking it to produce the correct nouns for a bunch of words is really just "tell me which case you saw most during training", which is something LLM's are really good at.
Re:GPT4 Can’t Ace MIT
by pmoriarty on Saturday June 17, 2023 @10:05PM
(#36376661)
From what I understand, it's trained mostly on English, and performs better in English. So it's not at all surprising it would make more mistakes in German or some other language.
It has probably seen the correct nouns used millions of times in the training data - and asking it to produce the correct nouns for a bunch of words is really just "tell me which case you saw most during training", which is something LLM's are really good at.