News for hackers. Stuff that matters.
Re:Jeopardy Game Using LLM and Python by jll29 on Thursday November 07, 2024 @02:12AM (#42074298)
"hallucination" here is a technical term for language model output that make no sense to the user.

They are the direct result of the way current neural language models work, namely based on a training regime where random words are "masked" (hidden) in sentences and the hidde word is presented with the sentence as the solution to a riddle to the large neural network that is the language model (large language model, LLM). Over time, the LLM learns what the hidden words could be in the form of a probability distribution. A related, similar training regime exists for predicting the next sentence, given a sentence.

Instead of modelling directly what the propositional/logical meaning of a sentence is, LLMs learn language only via such statistical properties, which Leech (1981) in his seminal book _Semantics_ (2nd ed.) called "associative meaning".

Occasional wrong, impossible and meaningless responses from LLMs are a result of that architecture, and people have dubbed that effect "hallucination", which I find a bit misleading because a crude mechanism is linguistically wrongly humanized, and there is a connotation with a person not functioning properly, which is even worse: it's a property of the model when it actually works as expected, just an undesired one at that.

Re:Jeopardy Game Using LLM and Python by jojobas on Thursday November 07, 2024 @02:48AM (#42074499)
Whoosh!
Re:Jeopardy Game Using LLM and Python by Bjartr on Thursday November 07, 2024 @08:05AM (#42076305)
As much as this missed the joke, I love how sincere this answer is.