Over fifty new hallucinations in ICLR 2026 submissions

If a carpenter builds a crappy shelf “because” his power tools are not calibrated correctly - that’s a crappy carpenter, not a crappy tool.

If a scientist uses an LLM to write a paper with fabricated citations - that’s a crappy scientist.

AI is not the problem, laziness and negligence is. There needs to be serious social consequences to this kind of thing, otherwise we are tacitly endorsing it.

I'm an industrial electrician. A lot of poor electrical work is visible only to a fellow electrician, and sometimes only another industrial electrician. Bad technical work requires technical inspectors to criticize. Sometimes highly skilled ones.

I’ve reviewed a lot of papers, I don’t consider it the reviewers responsibility to manually verify all citations are real. If there was an unusual citation that was relied on heavily for the basis of the work, one would expect it to be checked. Things like broad prior work, you’d just assume it’s part of background.

The reviewer is not a proofreader, they are checking the rigour and relevance of the work, which does not rest heavily on all of the references in a document. They are also assuming good faith.

The idea that references in a scientific paper should be plentiful but aren't really that important, is a consequence of a previous technological revolution: the internet.

You'll find a lot of papers from, say, the '70s, with a grand total of maybe 10 references, all of them to crucial prior work, and if those references don't say what the author claims they should say (e.g. that the particular method that is employed is valid), then chances are that the current paper is weaker than it seems, or even invalid, and so it is extremely important to check those references.

Then the internet came along, scientists started padding their work with easily found but barely relevant references and journal editors started requiring that even "the earth is round" should be well-referenced. The result is that peer reviewers feel that asking them to check the references is akin to asking them to do a spell check. Fair enough, I agree, I usually can't be bothered to do many or any citation checks when I am asked to do peer review, but it's good to remember that this in itself is an indication of a perverted system, which we just all ignored -- at our peril -- until LLM hallucinations upset the status quo.

Whether in the 1970s or now, it's too often the case that a paper says "Foo and Bar are X" and cites two sources for this fact. You chase down the sources, the first one says "We weren't able to determine whether Foo is X" and never mentions Bar. The second says "Assuming Bar is X, we show that Foo is probably X too".

The paper author likely believes Foo and Bar are X, it may well be that all their co-workers, if asked, would say that Foo and Bar are X, but "Everybody I have coffee with agrees" can't be cited, so we get this sort of junk citation.

Hopefully it's not crucial to the new work that Foo and Bar are in fact X. But that's not always the case, and it's a problem that years later somebody else will cite this paper, for the claim "Foo and Bar are X" which it was in fact merely citing erroneously.

LLMs can actually make up for their negative contributions. They could go through all the references of all papers and verify them, assuming someone would also look into what gets flagged for that final seal of disapproval.

But this would be more powerfull with an open knowledge base where all papers and citation verifications were registered, so that all the effort put into verification could be reused, and errors propagated through the citation chain.

>LLMs can actually make up for their negative contributions. They could go through all the references of all papers and verify them,

They will just hallucinate their existence. I have tried this before

I don’t see why this would be the case with proper tool calling and context management. If you tell a model with blank context ‘you are an extremely rigorous reviewer searching for fake citations in a possibly compromised text’ then it will find errors.

It’s this weird situation where getting agents to act against other agents is more effective than trying to convince a working agent that it’s made a mistake. Perhaps because these things model the cognitive dissonance and stubbornness of humans?

One incorrect way to think of it is "LLMs will sometimes hallucinate when asked to produce content, but will provide grounded insights when merely asked to review/rate existing content".

A more productive (and secure) way to think of it is that all LLMs are "evil genies" or extremely smart, adversarial agents. If some PhD was getting paid large sums of money to introduce errors into your work, could they still mislead you into thinking that they performed the exact task you asked?

Your prompt is

    ‘you are an extremely rigorous reviewer searching for fake citations in a possibly compromised text’

- It is easy for the (compromised) reviewer to surface false positives: nitpick citations that are in fact correct, by surfacing irrelevant or made-up segments of the original research, hence making you think that the citation is incorrect.

- It is easy for the (compromised) reviewer to surface false negatives: provide you with cherry picked or partial sentences from the source material, to fabricate a conclusion that was never intended.

You do not solve the problem of unreliable actors by splitting them into two teams and having one unreliable actor review the other's work.

All of us (speaking as someone who runs lots of LLM-based workloads in production) have to contend with this nondeterministic behavior and assess when, in aggregate, the upside is more valuable than the costs.