The exact phrase appears in the title. There is a title length limit. In this case, I don't think that it is wrong to pick the most interesting piece of that title that fits in the limit.
The "platonic representation hypothesis" crowd can't stop winning.
Potentially useful for things like innate mathematical operation primitives. A major part of what makes it hard to imbue LLMs with better circuits is that we don't know how to connect them to the model internally, in a way that the model can learn to leverage.
Having an "in" on broadly compatible representations might make things like this easier to pull off.
You seem to be going off the title which is plainly incorrect and not what the paper says. The paper demonstrates HOW different models can learn similar representations due to "data, architecture, optimizer, and tokenizer".
"How Different Language Models Learn Similar Number Representations" (actual title) is distinctly different from "Different Language Models Learn Similar Number Representations" - the latter implying some immutable law of the universe.
"using periodic features with dominant periods at T=2, 5, 10" seems inconsistent with "platonic representation" and more consistent with "specific patterns noticed in commonly-used human symbolic representations of numbers."
Edit: to be clear I think these patterns are real and meaningful, but only loosely connected to a platonic representation of the number concept.
The "platonic representation" argument is "different models converge on similar representations because they are exposed to the same reality", and "how humans represent things" is a significant part of reality they're exposed to.
you're right, its just that 'platonic' is an argument that numbers exist in the universe as objects in and of themselves, completely independent of human reality. if we don't assume this, that numbers are a system that humans created (formalism), then sure, we can be happy that llms are picking common representations that map well into our subjective notions of what numbers are.
Regardless of whether the convergence is superficial or not, I am interested especially in what this could mean for future compression of weights. Quantization of models is currently very dumb (per my limited understanding). Could exploitable patterns make it smarter?
Saw similar study comparing brain scans of person looking at image, to neural network capturing an image. And were very 'similar'. Similar enough to make you go 'hmmmm, those look a lot a like, could a Neural Net have a subjective experience?'
"Subjective experience" is "subjective" enough to be basically a useless term for any practical purpose. Can't measure it really, so we're stuck doing philosophy rather than science. And that's an awful place to be in.
That particular landmine aside, there are some works showing that neural networks and human brain might converge to vaguely compatible representations. Visual cortex is a common culprit, partially explained by ANN heritage perhaps - a lot of early ANN work was trying to emulate what was gleaned from the visual cortex. But it doesn't stop there. CNNs with their strong locality bias are cortex-alike, but pure ViTs also converge to similar representations to CNNs. There are also similarities found between audio transformers and auditory cortex, and a lot more findings like it.
We don't know how deep the representational similarity between ANNs and BNNs runs, but we see glimpses of it every once in a while. The overlap is certainly not zero.
Platonic representation hypothesis might go very far, in practice.
As someone actively researching in the neuroscience field these ideas are increasingly questionable. They do do a decent job of job of predicting neural data depending on your definition and if you compare them to hand built sets of features but we’re actually not even sure that will stay true. Especially in vision we already know that as models have scaled up they actually diverge more from humans and use quite different strategies. If you want them to act like humans or better reflect neural data you have to actively shape the training process to make that happen. There’s less we know about the language side of things currently though as that part of the field hasn’t yet really figured out exactly what they’re looking at yet because we generally know less about language in the brain vs vision. I think most vision scientists are on board with the idea that these things have really been diverging and have to be coerced to be useful. Language it’s more up in the air but there’s a growing wave of papers lately that seem to call the human LLM alignment idea into question. Personally I think the platonic representation idea is just a function of the convergence of training methods, data, and architectures all of these different labs are using. If you look at biological brains across species and even individuals within a species you see an incredible variety of strategies and representations that it seems ridiculous to me that anyone would suggest that there’s some base way to represent reality that is shared across everyone and every species. Here’s some articles that may be of interest if you’re curious:
I would expect that for any sampling of data that has a roughly similar distribution over many scales.
Which will be true of many human curated corpuses. But it will also be similar to, for natural data as well. Such as the lengths of random rivers, or the brightness of random stars.
The law was first discovered because logarithm books tended to wear out at the front first. That turned out to because most numbers had a small leading digit, and therefore the pages at the front were being looked up more often.
(Pardon the self promotion) Libraries like turnstyle are taking advantage of shared representation across models. Neurosymbolic programming : https://github.com/jdonaldson/turnstyle
Different models, similar number representations. Different models for different languages, similar concept representations. They have to learn all of this from human text input, so they're not divining it themselves. It all makes a strong case for universal grammar, IMO.
It's going to turn out that emergent states that are the same or similar in different learning systems fed roughly the same training data will be very common. Also predict it will explain much of what people today call "instinct" in animals (and the related behaviors in humans).
Evolution is an optimization process. So if platonic representation hypothesis holds well enough, there might be some convergence between ML neural networks and evolved circuits and biases in biological neural networks.
I'm partial to the "evolved low k-complexity priors are nature's own pre-training" hypothesis of where the sample efficiency in biological brains comes from.
This is just a result of base 10 being dominant in our natural languages.
I assume if we really used base 12, things would be different.
What would using base 12 in our natural language mean? Number names needed to be based on 12, not 10. Thirteen, twenty-seven, our numbers have base 10 embedded in their naming.
Potentially useful for things like innate mathematical operation primitives. A major part of what makes it hard to imbue LLMs with better circuits is that we don't know how to connect them to the model internally, in a way that the model can learn to leverage.
Having an "in" on broadly compatible representations might make things like this easier to pull off.
"How Different Language Models Learn Similar Number Representations" (actual title) is distinctly different from "Different Language Models Learn Similar Number Representations" - the latter implying some immutable law of the universe.
"How X happens" still implies that X happens, just adds additional explanation on top
I think the implications is slightly weaker -- it implies some immutable law of training datasets?
Edit: to be clear I think these patterns are real and meaningful, but only loosely connected to a platonic representation of the number concept.
The "platonic representation" argument is "different models converge on similar representations because they are exposed to the same reality", and "how humans represent things" is a significant part of reality they're exposed to.
Saw similar study comparing brain scans of person looking at image, to neural network capturing an image. And were very 'similar'. Similar enough to make you go 'hmmmm, those look a lot a like, could a Neural Net have a subjective experience?'
That particular landmine aside, there are some works showing that neural networks and human brain might converge to vaguely compatible representations. Visual cortex is a common culprit, partially explained by ANN heritage perhaps - a lot of early ANN work was trying to emulate what was gleaned from the visual cortex. But it doesn't stop there. CNNs with their strong locality bias are cortex-alike, but pure ViTs also converge to similar representations to CNNs. There are also similarities found between audio transformers and auditory cortex, and a lot more findings like it.
We don't know how deep the representational similarity between ANNs and BNNs runs, but we see glimpses of it every once in a while. The overlap is certainly not zero.
Platonic representation hypothesis might go very far, in practice.
[1] https://arxiv.org/pdf/2211.04533 [2] https://www.nature.com/articles/s41586-025-09631-6 [3] https://www.biorxiv.org/content/10.1101/2025.03.09.642245v1
Which will be true of many human curated corpuses. But it will also be similar to, for natural data as well. Such as the lengths of random rivers, or the brightness of random stars.
The law was first discovered because logarithm books tended to wear out at the front first. That turned out to because most numbers had a small leading digit, and therefore the pages at the front were being looked up more often.
What about through the lens of the Norvig-Chomsky debate?
I'm partial to the "evolved low k-complexity priors are nature's own pre-training" hypothesis of where the sample efficiency in biological brains comes from.
This proves a decimal system is correct. Base twelve numeral systems are clearly unnatural and inefficient.
What would using base 12 in our natural language mean? Number names needed to be based on 12, not 10. Thirteen, twenty-seven, our numbers have base 10 embedded in their naming.
It's still used for numbers between 70-99 in French, which is maddening when trying to copy down a phone number as a non-native speaker.