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

Disagreement among frontier LLMs on real-world fact-checks

lenz.io

Post reply on HN
Print view View original

191–200 of 377 posts

Re: Disagreement among frontier LLMs on real-world fact-checks

#191

Post by onceonceonce »

kostaj wrote: post #99
daveguy wrote: post #91

Earlier quoted context omitted.

Better options would have been "True", "False", "Unknown" (which opinions would fall under too). That also includes an interesting assessment of how well LLMs can identify missing information. My guess is they would be a very low number of "unknown" and a much higher level of agreement (assuming equal representation). Unless the RLHF techniques have gotten better at getting an LLM to say "I don't know", which I doubt…

Tried initially with a fifth bucket, Abstain. It was actually heavily used by some of the models. But it felt as if they are using this to "avoid" some of the hard questions, and we dropped this bucket to force them to provide a verdict.

Teams I work with use the abstain rate to flag what goes to a human. Disagreement between models is the same idea. Your 67% is what makes "two cheap models, escalate when they fight" actually work. Without abstain it mostly looks like noise.

Re: Disagreement among frontier LLMs on real-world fact-checks

#193

Post by drtz »

jawns wrote: post #103

"Extraterrestrial life exists somewhere in the universe." GPT-5.4: Misleading Opus 4.7: Misleading Gemini 3: FALSE Gemini 3 (Retrieval): FALSE Sonar Pro: FALSE It's a weird fact claim, because the ground truth is "nobody knows for sure" and that's not one of the available options.

> It's a weird fact claim, because the ground truth is "nobody knows for sure" and that's not one of the available options.

It's even weirder to suggest that the disagreement is indicative of a problem. If you asked five very knowledgeable humans on this subject to select the correct answer on a multiple-choice questionnaire, they would almost certainly vary significantly more than these 5 LLMs.

Not to say that hallucination isn't a problem, but this is a lousy way to test it.

Re: Disagreement among frontier LLMs on real-world fact-checks

#194

Post by aspenmartin »

kostaj wrote: post #78
segmondy wrote: post #69

Earlier quoted context omitted.

Yup, if anything this should be a guide on how not to eval a model. Furthermore, let's say the labels were non ambiguous, why would we care about alignment between the models? The only number I would personally care about is percentage of correct answers so I know which models to pick. I reckon with clear and non ambiguous prompts that we would see huge agreement if not 100% on real world facts. The huge models are s…

This paper covers only the disagreement between models and established only the floor of the error, based on the disagreement, but not which model is better. Planning to follow up with another study to benchmark against human-labelled verdicts still using a corpus that the models have not seen during training.

You also need to involve better measures of agreement that are standard in the literature like krippendorfs alpha with ordinal metric. So many footguns in this methodology

Re: Disagreement among frontier LLMs on real-world fact-checks

#195

Post by aspenmartin »

mgrunwald_ wrote: post #192

As an example, 2026 GPT doesn't even agree with its 2025 self. Last year I asked it to make a hardware comparison and it correctly identified the objectively better option. Recently I asked again and this time it got everything completely backwards.

Models are stochastic. Did you look at pass@k? I wouldn’t be surprised if you saw a regression because these models are extremely complex and impact of various decision making downstream is complex.

Re: Disagreement among frontier LLMs on real-world fact-checks

#197

Post by aspenmartin »

utopiah wrote: post #51

Don't forget people Goodhart's law will make this "benchmark" moot in weeks if not days. It will get integrated back into the fold, it will look "solved" but there will still be no reasoning, just more statistical technical correctness because light has be shown on a new "problem" to solve. It will then be clamored as great "progress" that will "change everything". PS: yes, I might or might not have a degree in corpo…

That is an effect but it’s not a nail in the coffin. There are lots of proprietary benchmarks on real product traffic that aren’t contaminated and open questions as well. People at these labs largely know what they are doing, it’s not like people don’t know this.

Re: Disagreement among frontier LLMs on real-world fact-checks

#198

Post by bastawhiz »

xyzzy123 wrote: post #143
simonw wrote: post #11

Here's the prompt they used: Classify this claim as of : " " Output exactly one label: True, Mostly True, Misleading, or False. No explanations, no qualifiers. The claims look like this: https://lenz.io/research/llm-disagreement/data.csv I put that in Datasette Lite to make it easier to explore. Here's an example of a disagreement: https://lite.datasette.io/?csv=https%3A%2F%2Fstatic.simonwil... The claim was "All alm…

> "On May 18, 2026, Ukraine carried out a drone attack on Moscow, Russia" I actually don't know which way you came down on that one? I think strictly it's false but "mostly true" would be justifiable? (as in, to say it's false would be misleading if it lead the reader to assume there was no attack around that time). https://www.washingtonpost.com/world/2026/05/17/ukrainian-dr... It seems it happened Saturday 16th ove…

That's ten days ago. As the commenter pointed out, without a web search tool there's no possible way for the model to know whether it's true or not, and the people conducting the study didn't give the models a way to respond with "I don't know".

Re: Disagreement among frontier LLMs on real-world fact-checks

#199

Post by ashirviskas »

andai wrote: post #44
simonw wrote: post #11

Here's the prompt they used: Classify this claim as of : " " Output exactly one label: True, Mostly True, Misleading, or False. No explanations, no qualifiers. The claims look like this: https://lenz.io/research/llm-disagreement/data.csv I put that in Datasette Lite to make it easier to explore. Here's an example of a disagreement: https://lite.datasette.io/?csv=https%3A%2F%2Fstatic.simonwil... The claim was "All alm…

Thanks. The first link is a spreadsheet. Here's a web-readable version. https://docs.google.com/spreadsheets/d/e/2PACX-1vSPLSv1P8Tqm...

I used AI to scrape the website and help build "Accuracy" comparison that everyone wants, thanks for this link!

https://docs.google.com/spreadsheets/d/e/2PACX-1vSnZlURmyYX3...

Re: Disagreement among frontier LLMs on real-world fact-checks

#200

Post by sibidharan »

kostaj wrote: post #99
daveguy wrote: post #91

Earlier quoted context omitted.

Better options would have been "True", "False", "Unknown" (which opinions would fall under too). That also includes an interesting assessment of how well LLMs can identify missing information. My guess is they would be a very low number of "unknown" and a much higher level of agreement (assuming equal representation). Unless the RLHF techniques have gotten better at getting an LLM to say "I don't know", which I doubt…

Tried initially with a fifth bucket, Abstain. It was actually heavily used by some of the models. But it felt as if they are using this to "avoid" some of the hard questions, and we dropped this bucket to force them to provide a verdict.

[dead]
Post reply on HN