Re:Introducing Agents in Haystack: Make LLMs resolve complex...
by ramraj07 on Monday April 03, 2023 @08:50PM
(#35433539)
Gpt-4 does a reasonable job citing things. It can’t cite every paper out there but definitely the well cited ones.
[ Parent
| on HN ]
Re:Introducing Agents in Haystack: Make LLMs resolve complex...
by PostOnce on Monday April 03, 2023 @08:52PM
(#35433559)
Does it cite papers that don't exist, or cite papers when the paper it cites doesn't actually contain the information being cited?
I would bet it does, at least some percent of the time.
Re:Introducing Agents in Haystack: Make LLMs resolve complex...
by ramraj07 on Monday April 03, 2023 @10:08PM
(#35434060)
The latter, yes. Interestingly I’m not surprised at all. This is what many researchers themselves do lol. I never take a reference at face value from any human being and I apply the same standard to gpt-4 as well. But all its references are real. Just 20-40% of time it might not exactly say the same as what I asked it for (though it’s related, and mostly there).
Re:Introducing Agents in Haystack: Make LLMs resolve complex...
by yosito on Tuesday April 04, 2023 @09:11AM
(#35439058)
I've been trying to get GPT-4 to give me accurate links to predictable websites. It gives me very plausible links, that even have the right domain and path format but often the plausible link is not the correct link and GPT-4 seems to have no awareness of the correct link.