7h ago

Aaron Roth flags phantom NeurIPS 2026 citation for 'Why Do Multi-Agent LLM Systems Fail?' that appeared in OpenReview and Google Scholar BibTeX exports

Paper presents MAST-Data of 1,600 multi-agent traces and 14-mode failure taxonomy.

0
Original post

A clearly hallucinated citation! NeurIPS 2026 decisions aren't out yet. But wait --- the hallucination is also present in the bibtex entries from openreview https://openreview.net/forum?id=fAjbYBmonr and Google Scholar https://scholar.googleusercontent.com/scholar.bib?q=info:E9WlfpJ70l0J:scholar.google.com/&output=citation&scisdr=CljIHctUENiogcez9JA:AFyMTJUAAAAAag217JCmKMR6XCw1ojwmwzHCQqA&scisig=AFyMTJUAAAAAag217DvWNBtTL4On8NPG9y8LQII&scisf=4&ct=citation&cd=-1&hl=en

6:21 AM · May 20, 2026 View on X

@Aaroth Yeaaaah... As someone who does try to contribute to responsible/ethical practices in AI, some of the "hallucination" policies miss the forest for the trees -- punishing people who aren't using LLMs at all....

MMitchellMMitchell@mmitchell_ai

Food for peer review thought: A citation isn’t “hallucinated” if it’s *grounded* on an actual paper. It may include hallucinated or incorrect *components* — eg, one author is wrong or the DOI is off by 1 — but the citation as a whole is not a “hallucination”.

3:26 PM · May 2, 2026 · 6.9K Views
5:22 PM · May 20, 2026 · 699 Views

Not defending the policy, but citations can be completely hallucinated too. Just ask the model to write a paragraph together with all the citations and additional bibtex entries. Of course, it's not something that I recommend, but I am pretty sure a lot of people do this. But, again, I don't approve draconian arxiv policy in this regard.

MMitchellMMitchell@mmitchell_ai

@Aaroth Yeaaaah... As someone who does try to contribute to responsible/ethical practices in AI, some of the "hallucination" policies miss the forest for the trees -- punishing people who aren't using LLMs at all....

5:22 PM · May 20, 2026 · 699 Views
5:57 PM · May 20, 2026 · 11 Views

@Aaroth At first I thought this was a regular NeurIPS error (they have tended up to mess up dates on their proceedings, and also the volume number), and then saw the date. This happens with Openreview for in review papers quite frequently.

Aaron RothAaron Roth@Aaroth

A clearly hallucinated citation! NeurIPS 2026 decisions aren't out yet. But wait --- the hallucination is also present in the bibtex entries from openreview https://openreview.net/forum?id=fAjbYBmonr and Google Scholar https://scholar.googleusercontent.com/scholar.bib?q=info:E9WlfpJ70l0J:scholar.google.com/&output=citation&scisdr=CljIHctUENiogcez9JA:AFyMTJUAAAAAag217JCmKMR6XCw1ojwmwzHCQqA&scisig=AFyMTJUAAAAAag217DvWNBtTL4On8NPG9y8LQII&scisf=4&ct=citation&cd=-1&hl=en

1:21 PM · May 20, 2026 · 15.4K Views
2:13 PM · May 20, 2026 · 1.2K Views