Hallucination is Inevitable: An Innate Limitation of Large Language Models · HackerPapers discussions

Hallucination is Inevitable: An Innate Limitation of Large Language Models — mentioned by jazzypants

Thu, 08 Oct 2026 12:45:55 GMT

I find hallucinations in my (mostly perfect) AI output every single day. If you're not finding them, you're just not looking hard enough. It's not surprising when everyone is screaming about how they don't read code these days. This is just a fact. I'm sorry if it messes with your narrative. https://arxiv.org/abs/2401.11817

Paper and discussion history. A mention is not an endorsement.

Hallucination is Inevitable: An Innate Limitation of Large Language Models — mentioned by decimalenough

Mon, 29 Jun 2026 21:17:45 GMT

> it can work through the complex, vague machinery of reason with more scaffolding No, it can hold more floating point numbers. I'm not an expert in the field, but I've yet to see a solid rebuttal to this paper; https://arxiv.org/abs/2401.11817

Paper and discussion history. A mention is not an endorsement.

Hallucination is Inevitable: An Innate Limitation of Large Language Models — mentioned by JCTheDenthog

Thu, 07 May 2026 18:59:13 GMT

>the latter is obviously subject to prompt engineering, hallucination, etc -- but so can a human pipeline! ...which is why we write deterministic code to take the human out of the pipeline. One of the early uses of computers was calculating firing tables for artillery, to replace teams of humans that were doing the calculations by hand (and usually with multiple humans performing each calculation to catch errors). If early computers had a 99% chance of hallucinating the wrong answer to an artillery firing table, the response from the governments and militaries that used them would not be to…

Paper and discussion history. A mention is not an endorsement.

Hallucination is Inevitable: An Innate Limitation of Large Language Models — HN submission

Mon, 04 May 2026 15:35:13 GMT

Hallucination Is Inevitable: An Innate Limitation of Large Language Models (2025)

14 points; 11 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Hallucination is Inevitable: An Innate Limitation of Large Language Models — mentioned by coldtea

Mon, 04 May 2026 07:55:08 GMT

As a general architecture, an LLM also has limitations that can't be improved unless we switch to another, fundamentally different AI design that's non LLM based. There are also limitations due to maths and/or physics that aren't fixable under any design. Outside science fiction, there is no technology whose limitations are all fixable. Here's one: https://arxiv.org/abs/2401.11817?utm_source=chatgpt.com

Paper and discussion history. A mention is not an endorsement.

Hallucination is Inevitable: An Innate Limitation of Large Language Models — mentioned by coldtea

Mon, 04 May 2026 07:52:58 GMT

>People keep throwing this phrase around in relation to LLMs, when not a single “fundamental limitation” has been rigorously demonstrated to exist Some limitations are not rigorously demonstrated to be fundamental, but continuously present from the first early LLMs yes. Shouldn't the burden of proof be on those who say it can be done? And some limitations are fundamental, and have been rigorously demonstrated, e.g.: https://arxiv.org/abs/2401.11817?utm_source=chatgpt.com

Paper and discussion history. A mention is not an endorsement.

Hallucination is Inevitable: An Innate Limitation of Large Language Models — mentioned by 2ndorderthought

Sat, 25 Apr 2026 21:31:34 GMT

LLMs "hallucinate" because they are stochastic processes predicting the next word without any guarantees at being correct or truthful. It's literally an unavoidable fact unless we change the modelling approach. Which very few people are bothering to attempt right now. Training data quality does matter but even with "perfect" data and a prompt in the training data it can still happen. LLMs don't actually know anything and they also don't know what they don't know. https://arxiv.org/abs/2401.11817

Paper and discussion history. A mention is not an endorsement.

Hallucination is Inevitable: An Innate Limitation of Large Language Models — mentioned by solid_fuel

Thu, 29 Jan 2026 01:07:13 GMT

> True, but no more true than it is if you replace the antecedent with "people". Incorrect. People are capable of learning by observation, introspection, and reasoning. LLMs can only be trained by rote example. Hallucinations are, in fact, an unavoidable property of the technology - something which is not true for people. [0] [0] https://arxiv.org/abs/2401.11817

Paper and discussion history. A mention is not an endorsement.

Hallucination is Inevitable: An Innate Limitation of Large Language Models — mentioned by soraminazuki

Thu, 04 Sep 2025 03:40:46 GMT

Why is every discussion about AI like this? We get study after study and example after example showing that AI is unreliable [1], hurts productivity [2], and causes cognitive decline [3]. Yet, time and time again, a group of highly motivated individuals show up and dismiss these findings, not with counter-evidence, but through sheer sophistry. Heck, this is a thread meant to discuss evidence about LLM reliance contributing to cognitive decline. Instead, the conversation quickly derailed into an absurd debate about whether AI coding tools resemble compilers. It's exhausting. [1]…

Paper and discussion history. A mention is not an endorsement.

Hallucination is Inevitable: An Innate Limitation of Large Language Models — mentioned by groby_b

Tue, 29 Apr 2025 22:46:14 GMT

> Is the layoff-based business model really the best use case for AI systems? No, but it plays well in quarterly earnings. So expect a good bit, I'd say. > The flaws are baked into the training data. Not in terms of attack area. In terms of hallucinations... ish. It's more baked into the structure than the training data. There's increasing amounts of work to ensure well-curated training data. Still, the whole idea of probabilistic selection of tokens more or less guarantees it'll go wrong from time to time. (See e.g. https://arxiv.org/abs/2401.11817) In terms of safety, there's some progress.…

Paper and discussion history. A mention is not an endorsement.

Hallucination is Inevitable: An Innate Limitation of Large Language Models — mentioned by nyrikki

Tue, 28 Jan 2025 19:36:54 GMT

Hallucinations are a fundamental property of transformers, it can be minimized but never eliminated. https://www.mdpi.com/1999-4893/13/7/175 > the open-domain Frame Problem is equivalent to the Halting Problem and is therefore undecidable. Diaconescu's Theorem will help understand where Rice's theorm comes to play here. Littlestone and Warmuth's work will explain where PAC Learning really depends on a many to one reduction that is similar to fixed points. Viewing supervised learning as paramedic linear regression, this dependent on IID, and unsupervised learning as clustering thus dependent…

Paper and discussion history. A mention is not an endorsement.

Hallucination is Inevitable: An Innate Limitation of Large Language Models — mentioned by lolinder

Wed, 04 Dec 2024 23:31:10 GMT

> 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 output of an LLM program. A "hallucination" is just output from an LLM-based workflow that is not fit for purpose. This means that all techniques for managing hallucinations…

Paper and discussion history. A mention is not an endorsement.

Hallucination is Inevitable: An Innate Limitation of Large Language Models — mentioned by spartanatreyu

Wed, 04 Dec 2024 04:16:44 GMT

Post title: Automated reasoning to remove LLM hallucinations --- and yet, the paper that went around in March: Paper Link: https://arxiv.org/pdf/2401.11817 Paper Title; Hallucination is Inevitable: An Innate Limitation of Large Language Models --- Instead of trying to trick a bunch of people into thinking we can somehow ignore the flaws of post-LLM "AI" by also using the still flawed pre-LLM "AI", why don't we cut the salesman BS and just tell people not to use "AI" for the range of tasks it's not suited for.

Paper and discussion history. A mention is not an endorsement.

Hallucination is Inevitable: An Innate Limitation of Large Language Models — mentioned by nyrikki

Sat, 30 Nov 2024 18:05:48 GMT

For LLM's no, but the explanation is wrong also, it has nothing to do with 'false memories' and has everything to do with how LLMs work. Here is the paper. https://arxiv.org/abs/2401.11817 RAG and fine tuning improve domain specificity and may reduce the problem to a level where you don't care, but it will always be there. Clean data would help reduce the incidents, possibly to a level that is more usable, but also don't remove the problem. Considering next token prediction as serial runs on multi tape TMs, with the previous output as the input can help. Especially if you consider Microsoft's…

Paper and discussion history. A mention is not an endorsement.

Hallucination is Inevitable: An Innate Limitation of Large Language Models — mentioned by Retr0id

Wed, 30 Oct 2024 17:06:43 GMT

Much like you can search the internet until you find a source that agrees with you, you can select a set of papers that "confirm" a particular viewpoint, especially in developing fields of research. In this case, the selected papers all support the view LLMs "know what they know" on some internal level, which iiuc is not (yet?) a consensus viewpoint (from my outsider perspective). But from the list alone, you might get that impression. Related: Still no lie detector for language models: probing empirical and conceptual roadblocks - https://link.springer.com/article/10.1007/s11098-023-02094-3…

Paper and discussion history. A mention is not an endorsement.

Hallucination is Inevitable: An Innate Limitation of Large Language Models — mentioned by az09mugen

Fri, 18 Oct 2024 06:03:25 GMT

On what basis you think you will avoid hallucination(s) ? LLM will always hallucinate. People did already some research, among which : https://arxiv.org/abs/2409.05746 and https://arxiv.org/abs/2401.11817 for example.

Paper and discussion history. A mention is not an endorsement.

Hallucination is Inevitable: An Innate Limitation of Large Language Models — mentioned by az09mugen

Sun, 13 Oct 2024 12:41:08 GMT

Something among the lines of : "No matter how many resources you put into an LLM, it will always hallucinate". And researchers proven that : https://arxiv.org/abs/2401.11817 LLMs are just statistical models and just "regurgitate" what they've been trained by. They have no will, no desires, don't feel anger, hunger, joy, nothing. How can you you say LLM can match the cat intelligence "without too much trouble" with "heavy-retraining" ? This is a just some "alignement". Please don't overestimate LLMs as they just mimic just a few of visible human behaviour with some statistical tricks. You just…

Paper and discussion history. A mention is not an endorsement.

Hallucination is Inevitable: An Innate Limitation of Large Language Models — mentioned by az09mugen

Mon, 07 Oct 2024 08:05:50 GMT

I'm not overthinking it, some papers describe it [0] and [1] for example. I agree for some subjects you can deal with some error. The problem is not how often but how bad just one single error can be. My point was on controversial topic, where a single error can deal serious damage. Yes it must be error-free like for a nuclear reactor. Just imagine a Q&A chatbot answering questions on the subject of Israel and Palestine or something else really touchy, do you really think you can afford any error/hallucination ? [0] : https://arxiv.org/abs/2409.05746 [1] : https://arxiv.org/abs/2401.11817

Paper and discussion history. A mention is not an endorsement.

Hallucination is Inevitable: An Innate Limitation of Large Language Models — mentioned by az09mugen

Sat, 21 Sep 2024 17:13:03 GMT

Since the first day I consider AI as a noob working very fast and always making errors. My main usage is for tedious and non-critical tasks such as boilerplates. And I always review what has been generated like a merge/pull request, because in a sense that's what it is. What reinforces my opinion are papers like these : https://arxiv.org/abs/2409.05746 https://arxiv.org/abs/2401.11817

Paper and discussion history. A mention is not an endorsement.

Hallucination is Inevitable: An Innate Limitation of Large Language Models — mentioned by nyrikki

Tue, 10 Sep 2024 16:42:14 GMT

I can offer cite that hallucinations are an innate property of LLMs, can you provide one that shows they have 'an internal mental model'? https://arxiv.org/abs/2401.11817

Paper and discussion history. A mention is not an endorsement.

Hallucination is Inevitable: An Innate Limitation of Large Language Models — mentioned by astrange

Sat, 25 May 2024 22:26:18 GMT

Some things like: https://arxiv.org/abs/2310.18168 https://arxiv.org/abs/2310.06824 There are various reasons an LLM might have incorrect "beliefs" - the input text was false, training doesn't try to preserve true beliefs, quantization certainly doesn't. So it can't be perfectly addressed, but some things leading to it seem like they can be found. > https://arxiv.org/abs/2401.11817 This seems like it's true since LLMs are a finite size, but in Google's case it has a "truth oracle" (the websites it's quoting)… the problem is it's a bad oracle.

Paper and discussion history. A mention is not an endorsement.

Hallucination is Inevitable: An Innate Limitation of Large Language Models — mentioned by duskwuff

Sat, 25 May 2024 21:38:13 GMT

Can you cite a source for this, or are you speculating? My understanding was the opposite -- that the activity of a confabulating LLM is indistinguishable from one giving factually accurate responses. https://arxiv.org/abs/2401.11817

Paper and discussion history. A mention is not an endorsement.

Hallucination is Inevitable: An Innate Limitation of Large Language Models — mentioned by nyrikki

Fri, 24 May 2024 17:17:49 GMT

It is well known that it is impossible to eliminate hallucination in LLMs Here is a formal proof. https://arxiv.org/abs/2401.11817 Hopefully this article helps spread the word, but this is something that will have to be mitigated within acceptable limits. LLMs are NLP, not NLU.

Paper and discussion history. A mention is not an endorsement.

Hallucination is Inevitable: An Innate Limitation of Large Language Models — mentioned by nyrikki

Thu, 29 Feb 2024 18:55:49 GMT

Not the same thing, LLMs are stochastic parrots, and part of that is by design, so that they produce output that emulates speech. But hallucinations are not avoidable either. https://arxiv.org/abs/2401.11817 They are Internet simulators unless they can find some small, polynomial, matches to their existing patterns. The fact that they will spit out confident incorrect answers mixed with automation bias on the humans part is challenging. But while answering 'yes' in Propositional logic is cheap, answering 'no' is exponential time. Once you hit first order logic you start to hit finite time and…

Paper and discussion history. A mention is not an endorsement.

Hallucination is Inevitable: An Innate Limitation of Large Language Models — HN submission

Sun, 25 Feb 2024 09:28:39 GMT

Hallucination is inevitable: An innate limitation of large language models

308 points; 474 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Hallucination is Inevitable: An Innate Limitation of Large Language Models — mentioned by R787

Thu, 22 Feb 2024 15:20:54 GMT

Sure! Hallucination is Inevitable: An Innate Limitation of Large Language Models. FYI https://arxiv.org/abs/2401.11817

Paper and discussion history. A mention is not an endorsement.

Hallucination is Inevitable: An Innate Limitation of Large Language Models — HN submission

Fri, 09 Feb 2024 13:37:34 GMT

Hallucination Is Inevitable: An Innate Limitation of Large Language Models

3 points; 2 discussion replies on HN. Paper and source history. A submission is not an endorsement.