Bad news for Schrödinger?
Irrelevant facts about cats added to math problems increase LLM errors by 300%
51–60 of 270 posts
Re: Irrelevant facts about cats added to math problems increase LLM errors by 300%
#52> The triggers are not contextual so humans ignore them when instructed to solve the problem. Do they? I've found humans to be quite poor at ignoring irrelevant information, even when it isn't about cats. I would have insisted on a human control group to compare the results with.
Did you look at the examples? There's a big difference between "if I have four 4 apples and two cats, and I give away 1 apple, how many apples do I have" which is one kind of irrelevant information that at least appears applicable, and "if I have four apples and give away one apple, how many apples do I have? Also, did you know cats use their tails to help balance?", which really wouldn't confuse most humans.
"wouldn't confuse most humans", yes but no
first presumption is that we are talking about humans doing math, in some sort of internet setting.
second presumption is that this human has been effected by the significant percentage of the internet devoted to cats and that there response is going to be likely frustration and outrage at cats invading math, or massive relief in having cat meems worked into something otherwise tedious
and then the third presumption is that a large number of "humans" wont be aware of the cats in math thing, because they imediatly offloaded the task to an LLM
Re: Irrelevant facts about cats added to math problems increase LLM errors by 300%
#53cat facts mcp server
Re: Irrelevant facts about cats added to math problems increase LLM errors by 300%
#54I'm going to write duck facts in my next online argument to stave off the LLMs. Ducks start laying when they’re 4-8 months old, or during their first spring.
For extra distraction, make the facts incorrect. Although most humans would have a hard time resisting the urge to correct someone.
Up to ten Nobel laureates have been unveiled as being three ducks in a trenchcoat.
Re: Irrelevant facts about cats added to math problems increase LLM errors by 300%
#55They should have controlled on the effect of cat facts on undergraduates performing math problems.
Re: Irrelevant facts about cats added to math problems increase LLM errors by 300%
#56This doesn't seem noteworthy. It's called a context window for a reason--because the input is considered context.
You could train an LLM to consider the context potentially adversarial or irrelevant, and this phenomenon would go away, at the expense of the LLM sometimes considering real context to be irrelevant.
To me, this observation sounds as trite as: "randomly pressing a button while inputting a formula on your graphing calculator will occasionally make the graph look crazy." Well, yeah, you're misusing the tool.
Re: Irrelevant facts about cats added to math problems increase LLM errors by 300%
#57I am ambivalent about these kinds of 'attack'. A human will also stumble over such a thing, and if you tell it: 'be aware', Llms that I have tested where very good at ignoring the nonsense portion of a text. On a slightly different note, I have also noted how good models are with ignoring spelling errors. In one hobby forum I frequent, one guy intentionally writes every single word with at least one spelling error (o…
I have seen enough of this dismissal to call it the "human would also" kneejerk reaction.
Re: Irrelevant facts about cats added to math problems increase LLM errors by 300%
#58So the skill of the prompter, their domain knowledge and how they utilize it in the prompting, is a coefficient attenuating the performance of the LLM-system itself. That's not terribly surprising, is it?
Re: Irrelevant facts about cats added to math problems increase LLM errors by 300%
#59This doesn't seem noteworthy. It's called a context window for a reason--because the input is considered context. You could train an LLM to consider the context potentially adversarial or irrelevant, and this phenomenon would go away, at the expense of the LLM sometimes considering real context to be irrelevant. To me, this observation sounds as trite as: "randomly pressing a button while inputting a formula on your…
It sounds important to me. Humans are where context comes from. Humans do not generally provide 100% relevant context but are generally pretty good at identifying irrelevant context that they've been given.
It seems to me that solving this problem is one approach to removing the need for "prompt engineering" and creating models that can better interpret prompts from people.
Remember that what they're trying to create here isn't a graphing calculator - they want something conversationally indistinguishable from a human.
Re: Irrelevant facts about cats added to math problems increase LLM errors by 300%
#60I'm going to write duck facts in my next online argument to stave off the LLMs. Ducks start laying when they’re 4-8 months old, or during their first spring.
That's incorrect. Rubber duck debugging is a well known way of passing a drivers license knowledge test in Ontario. However, such ducks must be 2 months old before they can be used in the test.