When LLM judges agree, should we believe them?

mey•19 minutes ago

A shared blind spot as noted at the bottom needs to be considered more often. In my day job, most of my coordination with others and now LLMs, is clarifying context and requirements. Claude is very happy to make assertions without the full picture in my experience, even when I give it as much context as I can.

qarl•about 1 hour ago

While this is absolutely true - I'd hesitate to discount using similar agents for checking each other. Two agents will almost never hallucinate in the same way, regardless of their weights - and by having a second one (with a different context) check almost entirely eliminates the problem.

emodendroket•34 minutes ago

It depends what we're judging, doesn't it? If it's "is the formatting in this document compliant with our standards?" I think it's reasonable. If it's like, life-altering if it's wrong I'm less sanguine.

Joel_Mckay•24 minutes ago

They have already shown algorithmic discrimination in predicting recidivism for brown people, as they are nonsensically overrepresented in the statistical data of US prison populations.

Folks should sue in a class-action lawsuit, any legal firm worth their beautiful walnut desks would seriously be happy take on that constitutionally backed mission. =3

bryzaguy•about 2 hours ago

They would all agree raspberry has two Rs

Joel_Mckay•43 minutes ago

But still refuse to answer "How many strings does a bass play with in water?" , perhaps the chat monitors in the third world data entry centers will manually patch the nonsense for a more rational answer someday. lol =3

wbobeirne•11 minutes ago

This was the first time I'd heard that gotcha question. I just threw it at Opus 5:

    None — a bass in water is a fish, and fish are notoriously bad at music.
    
    The instrument version plays four strings as standard (five and six-string basses exist for players who want to go lower or higher), and it prefers to stay dry.

Seems like a pretty good answer to me!

VaradD09•about 1 hour ago

I believe it depends on the LLM itself. Like what model as each model has diff weights and diff data trained onn

dgellow•about 1 hour ago

I would recommend to read the article, it’s actually more nuanced than the title

Tsarp•about 3 hours ago

Kinda weird to generalize "LLM". Every lab, every model is different. Has its own biases, reward functions etc.

ex1fm3ta•38 minutes ago

I kinda find it funny when I use the advisor on claude code and it agrees with the ideas that the previous model did.

For info: the advisor(s) available are higher end models. For example: you use sonnet, the available advisors are opus and fable. If you use Haiku, the advisor are sonnet, opus and fable.

nekusar•8 minutes ago

Betteridges law of headlines says "NO"

Founderarcstone•about 2 hours ago

Great point this will be interesting how this develops.

troupo•about 2 hours ago

Without reading the article (doesn't matter if it's pro or contra): no, of course not.

It shouldn't even be a debatable question.

dgellow•about 1 hour ago

I think you should have read the article first, at minimum the subheader

> Discounting the opinions of LLM judges with highly correlated outputs ensures that panels of judges reflect a true diversity of perspectives.

troupo•21 minutes ago

The quoted sentence still leads to the same answer: no.

Because there's no "discounting of opinions". They are running a separate LLM to "score" opinions. And the result is still "no" regardless of "lineages" or "sources".

And the end of the article leads me to believe that the entire article and approach is LLM-induced garbage:

--- start quote ---

When LLM judges agree, we should ask why. Sometimes agreement is independent evidence. Sometimes it is a shared blind spot. A good aggregation method should be able to tell the difference.

--- end quote ---

When LLM judges agree, should we believe them?

⚡ Community Insights

Discussion (18 Comments)Read Original on HackerNews