gold23
Re:GPTZero finds 100 new hallucinations in NeurIPS 2025 accepted papers
on Thursday January 22, 2026 @07:21PM (#46726846)
*expose the problem
Re:GPTZero finds 100 new hallucinations in NeurIPS 2025 accepted papers
on Thursday January 22, 2026 @06:36PM (#46726539)
Obviously a post on a startup's blog will be more editorialized than an academic paper. Still, this seems like an important discussion to have.
Re:GPTZero finds 100 new hallucinations in NeurIPS 2025 accepted papers
on Thursday January 22, 2026 @05:56PM (#46726193)
Nonetheless this investigation is important to anyone with a stronger desire to preserve intellectual honesty than disdain for a company trying to expand their offering.
Re:GPTZero finds 100 new hallucinations in NeurIPS 2025 accepted papers
on Thursday January 22, 2026 @05:51PM (#46726149)
It's not the equivalent of a typo. A typo would be immediately apparent to the reader. This is a semantic error that is much less likely to be caught by the reader.
Re:GPTZero finds 100 new hallucinations in NeurIPS 2025 accepted papers
on Thursday January 22, 2026 @05:48PM (#46726127)
Why don't you look at the actual article? There are several more egregious examples, e.g., the authors being cited as "John Smith and Jane Doe"