Hallucination is inevitable: An innate limitation of large language models

Re:Hallucination is inevitable: An innate limitation of larg... by nkrisc on Sunday February 25, 2024 @09:03AM (#39500900)

But they could, if they needed to. But most people don’t need to, so they don’t keep that information in their brains.

I can’t tell you the date of every time I clip my toenails, but if I had to could remember it.

[ Parent | on HN ]

Re:Hallucination is inevitable: An innate limitation of larg... by cultureswitch on Sunday February 25, 2024 @03:38PM (#39504504)

LLMs can remember their sources. It's just additional knowledge, there's nothing special about it.

When you ask an LLM to tell you the height of Mount Everest, it clearly has a map of mountains to heights, in some format. Using exactly the same mapping structure, it can remember a source document for the height.

[ Parent | on HN ]

Re:Hallucination is inevitable: An innate limitation of larg... by nkrisc on Friday March 01, 2024 @09:16PM (#39569202)

No, it “knows” that one of the tokens that commonly follows is “29,031 ft”.

[ Parent | on HN ]