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

281–290 of 377 posts

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

#281

Post by kostaj »

MattRogish wrote: post #234
kostaj wrote: post #208

Earlier quoted context omitted.

That's a valid point. During the preliminary research, we did try also more explicit prompts (with explanation for each of the 4 buckets), as well as a five-bucket rubric (with Abstain option). Will show in a follow-up paper how the concise vs explicit prompt impacts the distribution of the verdicts and the level of disagreement. One issue to note with the longer prompts is that they open to much room for discussion…

The other thing I suspect is that "Just give me True/False" cuts off a large amount of the search space a modern-day LLM uses to help it answer questions (you can see it in reasoning traces but the act of writing the explanation helps guide it toward a better answer and gives it better likelihood it backtracks on a bad decision). If you let it spew out an explanation along with the answer, I'm curious if the accuracy…

Good point. Will publish in the next version also the results with a prompt that allows the models to "think out loud" before providing the final verdict.

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

#282

Post by mr_luc »

Alifatisk wrote: post #125
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.

Isn't misleading the correct option here then?

I feel like you’re right, for instance depending on how you define the extra in extraterrestrial.

The space station, the Artemis capsule, microbes on interplanetary probes, etc.

It could technically be said in a sentence and be true, but it would be misleading to most people.

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

#284

Post by fooker »

nicce wrote: post #221
fooker wrote: post #203

I don't get why everyone is hellbent on getting LLMs to perform fact checking. This is not the technology for it. Sure it might sorta kinda work in some circumstances. That doesn't make it a good fit. Think of it like buying a refrigerator for storing clothes.

People ask questions to get answers. For me, it feels quite important? Especially when search engines start to push them?

Just because it is important for the use case does not mean we can make it work. It's a pretty well known fundamental limitation of the technology. No amount of elbow grease will get it there.

There's an interesting tradeoff here, a year or two ago maybe it got facts right 50% of the time. Everyone knew not to rely on it.

Now, suppose we are 90% of the way there, only technically proficient people would know not to trust it. (like not adding Internet Explorer toolbars! Or remembering to use ad blockers..)

A few years later, suppose we have spend a lot of money and effort getting it 99% of the way there, trusting it would be somewhat natural by then. And then for the important 1% of the situations, it would stand to cause real harm. 1% seems low, but for a million invocations, you'd have 10000 mistakes.

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

#285

Post by serial_dev »

It’s just shows that fact-checking is not a thing for 99% of the cases. It’s interesting to see it in LLMs, but it’s not unique to them.

The “fact checkers” pretend they are objective and authoritative, but they are not, they are just one more opinion.

For the research, the four classification options are too many, it should be true, false, and maybe “can’t be determined”.

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

#286

Post by HarHarVeryFunny »

harpastum wrote: post #23
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…

Without providing definitions of "True / Mostly True / Misleading / False" to each rater, I rate the article's claim that "Only one verdict bucket can be correct per claim" as false . Something can be simultaneously "misleading" and either true or false. Which category should something go in if it's "mostly false"? How much can something be wrong before it goes from "mostly true" to "false" (objectively, both have so…

> True / Mostly True / Misleading / False

> Which category should something go in if it's "mostly false"?

For some reason they have chosen to call that "Misleading" rather than a more symmetrical "Mostly False", but the intent seems clear enough.

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

#288

Post by simianwords »

testfrequency wrote: post #266
simianwords wrote: post #236

Earlier quoted context omitted.

How do you know it is trained to have a bias? In fact can I ask you to provide a single reproducable answer right now?

Assuming this isn’t a satire reply: https://www.pnas.org/doi/10.1073/pnas.2603294123 Hope this helps!

This doesn’t show grok as a model has bias but only that the product that uses grok has bias.

Even the referenced papers to show models can have bias don’t show anything about grok.

Overall you have given me zero evidence that grok model itself has some political bias.

FWIW I don’t mind bias but I haven’t seen evidence of it.

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

#289

Post by Gormo »

mock-possum wrote: post #228
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.

I would think ‘false’ is the only correct answer a there’s no evidence to prove the claim, so the claim is safely assumed false. Then again maybe that’s why I’m an atheist, not an agnostic?

"False" isn't correct in strict boolean terms either, since that implies that the inverse is true. Claiming "there is extraterrestrial life in the universe" is false is logically equivalent to claiming that "no extraterrestrial life exists anywhere in the universe" is true.

Both statements would have to be interpreted as "false" under your criteria, as neither has any evidence to substantiate it. That leads us to a logical contradiction in which a proposition and its inverse are both regarded as false.

If the statement is being interpreted as "it has been proven that extraterrestrial life exists somewhere in the universe", then it's acceptable to say this statement is false, but making evaluations that depend on an implicit qualifier isn't usually a good approach.

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

#290

Post by jermaustin1 »

kostaj wrote: post #145
hombre_fatal wrote: post #110

Earlier quoted context omitted.

Since the agents were instructed to not explain their answer, you can't know if their answer was reasonable or not.

The reason for the "No explanations, no qualifiers" in the prompt was to force the models to put the claim in one of the four buckets and answer with the bucket name only. It's a pure quantitive analysis (first in a series) and it does indeed lack the qualitative aspect.

structured output { "answer" : "Misleading", "reason" : "Almonds..." }

Have reason be optional and instruct it to only provide reason for the middle "Mostly True" or "Misleading".

Post reply on HN