News for hackers. Stuff that matters.

A comment on Hallucination is inevitable: An innate limitation of large language models. Parent comment

Re:Hallucination is inevitable: An innate limitation of larg... by username332211 on Sunday February 25, 2024 @02:33PM (#39503970)
The thing is, the usefulness of a question answering system is in answering questions people don't generally know. We don't need an answering system for things that are common knowledge.

And it's not uncommon that certain knowledge would be, well uncommon even among experts. Experts specialize.

Since the usefulness of ornithological examples is getting exhausted, let's say one out of a hundred lawyers works in bankruptcy. If you ask a million lawyers about the provisions of 11 USC § 1129 and only ten thousand know the answer, is the answer untrustworthy, just because bankruptcy lawyers are far rarer than civil and criminal lawyers?

[ Parent | on HN ]
Re:Hallucination is inevitable: An innate limitation of larg... by caditinpiscinam on Wednesday February 28, 2024 @01:02AM (#39534585)
I agree that without deeper reasoning skills it's not obvious how a model should handle this sort of situation. In the end, I'm not saying that fixing the hallucination issue is easy, but rather that hallucination might be better understood as a property of the training data everyone is using, rather than the models themselves.
[ Parent | on HN ]