Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

GPTZero finds 100 new hallucinations in NeurIPS 2025 accepted papers

gptzero.me

Post reply on HN
Print view View original

311–320 of 528 posts

Re: GPTZero finds 100 new hallucinations in NeurIPS 2025 accepted papers

#311

Post by azan_ »

gowld wrote: post #294
azan_ wrote: post #195

Earlier quoted context omitted.

The problem is that reproducing something is really, really hard! Even if something doesn't reproduce in one experiment, it might be due to slight changes in some variables we don't even think about. There are some ways to circumvent it (e.g. team that's being reproduced cooperating with reproducing team and agreeing on what variables are important for the experiemnt and which are not), but it's really hard. The solu…

Every time some easy "Reproducibility is hard / not worth the effort" I hear "The original research wasn't meaningful or valuable".

And that's true! It doesn't make sense to spend a lot of resources on reproducing things when there is low hanging fruit of just requiring better research in the first place.

Re: GPTZero finds 100 new hallucinations in NeurIPS 2025 accepted papers

#312

Post by bandrami »

parpfish wrote: post #158
vld_chk wrote: post #148

Earlier quoted context omitted.

In my mental model, the fundamental problem of reproducibility is that scientists have very hard time to find a penny to fund such research. No one wants to grant “hey I need $1m and 2 years to validate the paper from last year which looks suspicious”. Until we can change how we fund science on the fundamental level; how we assign grants — it will be indeed very hard problem to deal with.

In theory, asking grad students and early career folks to run replications would be a great training tool. But the problem isn’t just funding, it’s time. Successfully running a replication doesn’t get you a publication to help your career.

Grad students have this weird habit of eating food and renting places to live, though, so that's also money

Re: GPTZero finds 100 new hallucinations in NeurIPS 2025 accepted papers

#313

Post by bandrami »

godelski wrote: post #247
vld_chk wrote: post #148

Earlier quoted context omitted.

In my mental model, the fundamental problem of reproducibility is that scientists have very hard time to find a penny to fund such research. No one wants to grant “hey I need $1m and 2 years to validate the paper from last year which looks suspicious”. Until we can change how we fund science on the fundamental level; how we assign grants — it will be indeed very hard problem to deal with.

Funding is definitely a problem, but frankly reproduction is common. If you build off someone else's work (as is the norm) you need to reproduce first. But without repetition being impactful to your career and the pressure to quickly and constantly push new work, a failure to reproduce is generally considered a reason to move on and tackle a different domain. It takes longer to trace the failure and the bar is higher…

> If you build off someone else's work (as is the norm) you need to reproduce first.

Not if the result you're building off of is a model, you can just assume it

Re: GPTZero finds 100 new hallucinations in NeurIPS 2025 accepted papers

#314

Post by jvanderbot »

i_am_proteus wrote: post #268
j2kun wrote: post #238

I spot-checked one of the flagged papers (from Google, co-authored by a colleague of mine) The paper was https://openreview.net/forum?id=0ZnXGzLcOg and the problem flagged was "Two authors are omitted and one (Kyle Richardson) is added. This paper was published at ICLR 2024." I.e., for one cited paper, the author list was off and the venue was wrong. And this citation was mentioned in the background section of the pa…

>this error does make me pause to wonder how much of the rest of the paper used AI assistance And this is what's operative here. The error spotted, the entire class of error spotted, is easily checked/verified by a non-domain expert. These are the errors we can confirm readily, with obvious and unmistakable signature of hallucination. If these are the only errors, we are not troubled. However: we do not know if these…

The problem is, 10 years ago when I was still publishing even I would let an incorrect citation go through b/c of an old bibtex file or some such.

Re: GPTZero finds 100 new hallucinations in NeurIPS 2025 accepted papers

#315

Post by waldarbeiter »

My website of choice whenever I have to deal with references is dblp [1]. In my opinion more reliable than Google scholar in creating correct BibTeX. Also when searching for a paper you clearly see where it has been published or if it is only on arxiv.

[1] https://dblp.org/

Re: GPTZero finds 100 new hallucinations in NeurIPS 2025 accepted papers

#316

Post by j2kun »

fn-mote wrote: post #308
i_am_proteus wrote: post #268

Earlier quoted context omitted.

>this error does make me pause to wonder how much of the rest of the paper used AI assistance And this is what's operative here. The error spotted, the entire class of error spotted, is easily checked/verified by a non-domain expert. These are the errors we can confirm readily, with obvious and unmistakable signature of hallucination. If these are the only errors, we are not troubled. However: we do not know if these…

This seems like finding spelling errors and using them to cast the entire paper into doubt. I am unconvinced that the particular error mentioned above is a hallucination, and even less convinced that it is a sign of some kind of rampant use of AI. I hope to find better examples later in the comment section.

I actually believe it was an AI hallucination, but I agree with you that it seems the problem is far more concentrated to a few select papers (e.g., one paper made up more than 10% of the detected errors).

Re: GPTZero finds 100 new hallucinations in NeurIPS 2025 accepted papers

#318

Post by AlienRobot »

pacbard wrote: post #223

The ironic part about these hallucinations is that a research paper includes a literature review because the goal of the research is to be in dialogue with prior work, to show a gap in the existing literature, and to further the knowledge that this prior work has built. By using an LLM to fabricate citations, authors are moving away from this noble pursuit of knowledge built on the "shoulders of giants" and show that…

That's going to be the philosophical question of our times: do LLMs generate slop out of nowhere or does it simply amplify the slop machinery that was already there?

Re: GPTZero finds 100 new hallucinations in NeurIPS 2025 accepted papers

#319

Post by pas »

poszlem wrote: post #165
vld_chk wrote: post #148

Earlier quoted context omitted.

In my mental model, the fundamental problem of reproducibility is that scientists have very hard time to find a penny to fund such research. No one wants to grant “hey I need $1m and 2 years to validate the paper from last year which looks suspicious”. Until we can change how we fund science on the fundamental level; how we assign grants — it will be indeed very hard problem to deal with.

I often think we should movefrom peer review as "certification" to peer review as "triage", with replication determining how much trust and downstream weight a result earns over time.

grants should come with money and requirement for independent reproduction

academia is too fragmented and extremely inefficient

Re: GPTZero finds 100 new hallucinations in NeurIPS 2025 accepted papers

#320

Post by pas »

vld_chk wrote: post #148
cogman10 wrote: post #2

Yuck, this is going to really harm scientific research. There is already a problem with papers falsifying data/samples/etc, LLMs being able to put out plausible papers is just going to make it worse. On the bright side, maybe this will get the scientific community and science journalists to finally take reproducibility more seriously. I'd love to see future reporting that instead of saying "Research finds amazing che…

In my mental model, the fundamental problem of reproducibility is that scientists have very hard time to find a penny to fund such research. No one wants to grant “hey I need $1m and 2 years to validate the paper from last year which looks suspicious”. Until we can change how we fund science on the fundamental level; how we assign grants — it will be indeed very hard problem to deal with.

yes, this should be built-in to grants and publishing

of course the problem is that academia likes to assert its autonomy (and grant orgs are staffed by academia largely)

Post reply on HN