News for hackers. Stuff that matters.
Re:Detecting hallucinations in large language models using s... by PaulHoule on Monday June 24, 2024 @09:10AM (#40775598)
Logic has all its own problems. See "Godel, Escher, Bach" or ask why OWL has been around for 20 years and had almost no market share, or why people have tried every answer to managing asynchronous code other than RETE, why "complex event processing" is an obscure specialty and not a competitor to Celery and other task runners. Or for that matter why can't Drools give error messages that make any sense?
Re:Detecting hallucinations in large language models using s... by badrunaway on Monday June 24, 2024 @11:38AM (#40777355)
LLMs right now don't employ any logic. There can always be corners of "I don't know" or "I can't do that" - than the current system which is 100% confident in it's answer because it's not actually trying to match any constraint at all. So at some point the system will apply logic but may not be as formal as we do in pure math.
Re:Detecting hallucinations in large language models using s... by biomcgary on Monday June 24, 2024 @11:30AM (#40777241)
As a computational biologist, I've used ontologies quite a bit. They have utility, but there is a bit of an economic mismatch between their useful application and the energy required to curate them. You have some experience in this space. Do you think LLMs could speed up ontology / knowledge graph curation with expert review? Or, do you think structured knowledge has a fundamental problem limiting its use?