Dave5

One way to explain this is to realise that LLMs don’t learn about relationships between facts, but between tokens, the linguistic forms that Bender described. The tokens “Tom Cruise’s mother” are linked to the tokens “Mary Lee Pfeiffer”, but the reverse is not necessarily true. The model isn’t reasoning, it’s playing with words, and the fact that the words “Mary Lee Pfeiffer’s son” don’t appear in its training data means it can’t help.

https://www.theguardian.com/technology/article/2024/aug/06/ai-llms