←back to thread

Why language models hallucinate

(openai.com)
277 points simianwords | 4 comments | 06 Sep 25 07:41 UTC | HN request time: 0.996s | source
Show context
robotcapital ◴[07 Sep 25 01:38 UTC] No.45154570[source]▶
It’s interesting that most of the comments here read like projections of folk-psych intuitions. LLMs hallucinate because they “think” wrong, or lack self-awareness, or should just refuse. But none of that reflects how these systems actually work. This is a paper from a team working at the state of the art, trying to explain one of the biggest open challenges in LLMs, and instead of engaging with the mechanisms and evidence, we’re rehashing gut-level takes about what they must be doing. Fascinating.
replies(4): >>45154689 #>>45155695 #>>45155909 #>>45155983 #
1. zahlman ◴[07 Sep 25 01:56 UTC] No.45154689[source]▶
Calling it a "hallucination" is anthropomorphizing too much in the first place, so....
replies(2): >>45154752 #>>45155168 #
2. robotcapital ◴[07 Sep 25 02:11 UTC] No.45154752[source]▶
Right, that’s kind of my point. We call it “hallucination” because we don’t understand it, but need a shorthand to convey the concept. Here’s a paper trying to demystify it so maybe we don’t need to make up anthropomorphized theories.
replies(1): >>45169072 #
3. razzmatazmania ◴[07 Sep 25 03:34 UTC] No.45155168[source]▶
Confabulation is human behavioral phenomena that is not all that uncommon. Have you ever heard a grandpa big fish story? Have you ever pretended to know something you didn't because you wanted approval or to feel confident? Have you answered a test question wrong when you thought you were right? What I find fascinating about these models is they are already more intelligent and reliable than the worst humans. I've known plenty of people who struggle to conceptualize and connect information and are helpless outside of dealing with familiar series of facts or narratives. That these models aren't even as large as human brains makes me suspect that practical hardware limits might still be in play here.
4. player1234 ◴[08 Sep 25 14:51 UTC] No.45169072[source]▶
We do nothing, they call it hallucination to decieve.

Altman simping all over.