Everything an LLM returns is an hallucination, it's just that some of those hallucinations line up with reality
AI hallucinations: Why LLMs make things up (and how to fix it)
11–20 of 257 posts
Re: AI hallucinations: Why LLMs make things up (and how to fix it)
#12Everything an LLM returns is an hallucination, it's just that some of those hallucinations line up with reality
The same is true for humans
Re: AI hallucinations: Why LLMs make things up (and how to fix it)
#13"Why LLMs do the one and only thing they do (and how to fix it)"
Re: AI hallucinations: Why LLMs make things up (and how to fix it)
#14the only comment on the prior submission 3 days ago summarizes the whole thing: https://news.ycombinator.com/item?id=42285149 Also, I saw any such blog title as "how to make money in the stock market:" friend, if you knew the answer you wouldn't blog about it you'd be infinitely rich
They don't say how to make big money, don't they? Also, the tl;dr is index funds and patience.
Re: AI hallucinations: Why LLMs make things up (and how to fix it)
#15When people talk about stopping an LLM from "seeing hallucinations instead of the truth", that's like stopping an Ouija-board from "channeling the wrong spirits instead of the right spirits." It suggests a qualitative difference between desirable and undesirable operation that isn't really there. They're all hallucinations, we just happen to like some of them more than others.
That's just not true.
The training data is the underlying truth and that's not nothing but a lot.
And hallucinations are pathes inside this space which are there for yet unknown reason.
We like answers from LLMs which walk through this space reasonable.
Re: AI hallucinations: Why LLMs make things up (and how to fix it)
#16The article referenced the Oxford semantic entropy study but failed to clarify that the issue greatly simplifies LLM hallucination (making most of the article outdated).
When we are not sure of an answer we have two choices: say the first thing that comes to mind (like an LLM), or say "I'm not sure".
LLMs aren't easily trained to say "I'm not sure" because that requires additional reasoning and introspection (which is why CoT models do better); hence hallucinations occur when training data is vague.
So why not just measure uncertainty in the tokens themselves? Because there are many ways to say the same thing, so a high entropy answer may only reflect uncertainty in synonyms-- many ways to say the same thing.
The paper referenced works to eliminate semantic similarity from entropy measurements, leaving much more useful results, proving that hallucination is conceptually a simple problem.
Re: AI hallucinations: Why LLMs make things up (and how to fix it)
#17Earlier quoted context omitted.
My go-to to show people who don't understand its limitations used to be the old "how many Ms are there in the word 'minimum' or something along those lines, but looks like it's gotten a bit better at that. I just tried it with GPT4o and it gave me the right number, but the wrong placement. In the past it's given it completely wrong: >how many instances of the letter L are in the word parallel The word parallel contai…
They probably have a letter counting tool added to it now. that it just knows to call when asked to do this. you ask it the number of letters and it sends those words off to another tool to count instances of L, but they didn't add a placement one so it's still guessing those. edit: corrected some typos and phrasing. Maybe we'll reach a point where the LLM's are just tool calling models and not really giver their own…
they probably just forgot to tell it humans are 1 indexed and to do the friendly conversion for them.
Re: AI hallucinations: Why LLMs make things up (and how to fix it)
#18Earlier quoted context omitted.
My go-to to show people who don't understand its limitations used to be the old "how many Ms are there in the word 'minimum' or something along those lines, but looks like it's gotten a bit better at that. I just tried it with GPT4o and it gave me the right number, but the wrong placement. In the past it's given it completely wrong: >how many instances of the letter L are in the word parallel The word parallel contai…
They probably have a letter counting tool added to it now. that it just knows to call when asked to do this. you ask it the number of letters and it sends those words off to another tool to count instances of L, but they didn't add a placement one so it's still guessing those. edit: corrected some typos and phrasing. Maybe we'll reach a point where the LLM's are just tool calling models and not really giver their own…
There are only 5 tools it has available to call, and that isn't one of them. A GitHub (forgot the url) stays up to date with the latest dumped system instructions.
Re: AI hallucinations: Why LLMs make things up (and how to fix it)
#19When people talk about stopping an LLM from "seeing hallucinations instead of the truth", that's like stopping an Ouija-board from "channeling the wrong spirits instead of the right spirits." It suggests a qualitative difference between desirable and undesirable operation that isn't really there. They're all hallucinations, we just happen to like some of them more than others.
The problem is that LLMs are just convincing enough that people DO trust them which is sort of a problem since AI slop is creeping into everything. What can be done to solve it (while not perfect) is pretty powerful. You can force feed them the facts (RAG) and then verify the result. Which is way better than trusting LLMs while doing neither of those things (which is what a lot of people do today anyway). See the rec…
How do you check it?
Take the example of case law. Would you need to formalize the entirety of case law? Would the AI then need to produce a formal proof of its argument, so that you can ascertain that its citations are valid? How do you know that the formal proof corresponds to whatever longform writing you ask the AI to generate? Is this really something that LLMs are suited for? That the law is suited for?
Re: AI hallucinations: Why LLMs make things up (and how to fix it)
#20[dead]