I am honestly very skeptical of articles like these. Hallucinations are a feature of LLMs. The only ways to "FIX" it is to either stop using LLMs. Or use a super bias some how.
AI hallucinations: Why LLMs make things up (and how to fix it)
61–70 of 257 posts
Re: AI hallucinations: Why LLMs make things up (and how to fix it)
#62> While the hallucination problem in LLMs is inevitable [0], they can be significantly reduced... Every article on hallucinations needs to start with this fact until we've hammered that into every "AI Engineer"'s head. Hallucinations are not a bug—they're not a different mode of operation, they're not a logic error. They're not even really a distinct kind of output. What they are is a value judgement we assign to the…
LLMs outputs are no more "hallucinations" than my output would be if I were asked to judge a dressage competition.
I’ve had multiple occasions where I’ve asked an LLM how to do in Java and it’ll very confidently answer to use . It would be far more helpful to me to receive an answer like “I don’t think there’s a third party library that does this, you’ll have to write it yourself” than to waste my time telling me a lie. If anything, calling these outputs “hallucinations” is a very polite way of saying that the LLM is bullshitting the user.
Re: AI hallucinations: Why LLMs make things up (and how to fix it)
#63I am honestly very skeptical of articles like these. Hallucinations are a feature of LLMs. The only ways to "FIX" it is to either stop using LLMs. Or use a super bias some how.
You should be. I don’t know anything about kepa.ai but before even clicking the article I assume they’re trying to sell me something. And “how to fix it” makes me think this is some kind of SEO written for people who think it can be fixed, meaning the article is written for robots and amateurs.
Re: AI hallucinations: Why LLMs make things up (and how to fix it)
#64> While the hallucination problem in LLMs is inevitable [0], they can be significantly reduced... Every article on hallucinations needs to start with this fact until we've hammered that into every "AI Engineer"'s head. Hallucinations are not a bug—they're not a different mode of operation, they're not a logic error. They're not even really a distinct kind of output. What they are is a value judgement we assign to the…
‘ I always struggle a bit with I'm asked about the "hallucination problem" in LLMs. Because, in some sense, hallucination is all LLMs do. They are dream machines. ...’
Re: AI hallucinations: Why LLMs make things up (and how to fix it)
#65Wow, a whole article that didn't mention the word "sampler" once. There's pretty strong evidence coming out that truncation samplers like min_p and entropix are strictly superior to previous samplers (which everyone uses like top_p) to prevent hallucinations and that LLMs usually "know" when they are "hallucinating" based on their logprobs.
https://openreview.net/forum?id=FBkpCyujtS (min_p sampling, note extremely high review scores)
https://github.com/xjdr-alt/entropix (Entropix)
Re: AI hallucinations: Why LLMs make things up (and how to fix it)
#66Earlier 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…
Here's QwQ-32 answering the same question. I'm including the entire answer here including the CoT: > Let's see. The word is "parallel." I need to count how many times the letter "L" appears in it. Okay, spelling it out: P-A-R-A-L-L-E-L. So, starting from the beginning, first letter is P, not L. Then A, not L. R, not L. Another A, still not L. Then L, that's one L. Next letter is L again, so that's two L's. Then E, no…
> If the word was "paralell," that would be four L's, but that's not the correct spelling.
Better but this is still a hallucination.
Re: AI hallucinations: Why LLMs make things up (and how to fix it)
#67Earlier quoted context omitted.
Correct. That but for 1000. You can build your own with any number of online tools. I don't have a link because it's part of a lesson plan set behind a payment on teachers pay teachers.
Do you have a link to any of those online tools that can be used to generate a puzzle of equivalent complexity to the one that you've tested on?
The sum doesn’t even have to be 1000, just create a grid of random numbers, create a random path and find the sum. It’s an equivalent problem.
Re: AI hallucinations: Why LLMs make things up (and how to fix it)
#68The debate around "fixing" hallucinations reminds me of the debate around schizophrenia.
https://www.youtube.com/watch?v=nEnklxGAmak
It's not a single thing, a specific defect, but rather a failure mode, an absence of cohesive intelligence.
Any attempt to fix a non-specific ailment (schizophrenia, death, old age, hallucinations) will run into useless panaceas.
Re: AI hallucinations: Why LLMs make things up (and how to fix it)
#69When 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.
I disagree with this take, Stallman has expressed it recently by linking some "scientific article".
While I get that LLMs generate text in some way that does not guarantee correctness. There is a correlation between generated text and correctness, which is why millions of people use it...
You can judge the correctness of a sentence generated by an LLM. In the same way you can judge the correctness of a human generated sentence.
Now whether the truthness or correlation with reality of an LLM sentence can be judged on its own or whether it requires a human to interpret it is not very relevant, as sentences produced by the LLM are still correct most of the time. Just because it is not perfect doesn't make the correctness in the other cases useless, albeit perhaps less useful of course.
This is nothing surprising of a statistical model, it tends to produce true results.
Re: AI hallucinations: Why LLMs make things up (and how to fix it)
#70Everything an LLM returns is an hallucination, it's just that some of those hallucinations line up with reality
How are you defining hallucination then? In some pretty useless way inevitably.
Hallucinations are precisely the generated expressions that don't correlate with reality or are not truthful.