Natural language instructions induce generalization in networks of neurons

https://www.nature.com/articles/s41593-024-01607-5

by birriel • 2 years ago

186 89 2 years ago

kevindamm• 2 years ago

It's as if language is itself the latent space for these psychophysical tasks, especially compositional instruction. Their description of it as a scaffolding also seems apt.

zer00eyz2• 2 years ago

I hate the reductive nature of the concept of "latent spaces".

A good enough formula for a task isn't a solution for every task. Yes Newtonian mechanics work, but Einstein is a better reflection of reality.

bongodongobob• 2 years ago

I'm not sure I understand the analogy. The very idea of NNs is that it's not perfect, it is messy and not optimal, but is very generalizable.

nerdponx2• 2 years ago

The entire innovation (discovery?) of LLMs is that a good formula for the task of sequence completion turns out to also be a good formula for a wide range of AI tasks. That emergent property is why language models are called language models.

nothis• 2 years ago

I'm not pretending to understand half the words uttered in this discussion but I'm constantly reminded of how much it helps me to articulate things (explain them to others, write them down, etc) to understand them. Maybe that thinking indeed happens almost entirely on a linguistic level and I'm not doing half as much other thinking (visualization, abstract logic, etc.) in the process as I thought. That feels weird.

robwwilliams3• 2 years ago

Or is the real thinking sub-linguistic and “you” and those you talk to are the target audience of language? Sentences emerge from a pre-linguistic space we do not understand.

mrblah3• 2 years ago

i've always assumed that language was required to give your brain the abstractions needed to reference things in the past compared to your current perception (aka now), like an index. if you think about your earliest memories, they almost certainly came after language. i'd be interested to know if any of the documented 'wild child' cases (infants 'raised by wolves') ever delved into what the children remembered before, after being taught language as an adolescent.

tsimionescu2• 2 years ago

There were efforts to teach them language as adolescents, but they didn't acquire it - as far as we know, it's not possible to acquire language if you don't do it as an infant.

This is similar to other brain functions that aren't present at birth and require stimulation, such as sight. That is, if your eyes are forced closed for the first few months of your life, you will never be able to see, even if later they are uncovered, and keep working perfectly. The brain functions responsible for interpreting visual signals can only develop if they get visual signals in a (quite short) developmental window - and we know this with quite a bit of certainty from quite cruel animal studies.

Language acquisition is not proven to be the same, as the required studies would be deeply unethical, but the few experiences with feral children are highly suggestive that the same applies.

jameshart4• 2 years ago

We found that language scaffolds sensorimotor representations such that activity for interrelated tasks shares a common geometry with the semantic representations of instructions, allowing language to cue the proper composition of practiced skills in unseen settings.

Sapir-Whorf with the surprise comeback?

sisyphus_coding• 2 years ago

comeback

Did it fall out of favour?

jameshart4• 2 years ago

Strong Sapir-Whorf (linguistic determinism - language constrains thought) became pretty much seen as a joke by the 1980s. Linguistic relativism (weak Sapir-Whorf - language shapes thought) is still respectable (because, I mean, of course it does).

Actually, this research might just as well be evidence for linguistic universalism (Chomsky - language enables thought).

In general linguistic philosophers have been coming out with either laughably obvious or utterly untestable hypotheses for a century and it’s amusing to see how these AI studies shake up the hornets.

nyrikki2• 2 years ago

Tasks that are instructed using conditional clauses also require a simple form of deductive reasoning (if p then q else s)
Our models ofer several experimentally testable predictions outlining how linguistic information must be represented to facilitate flexible and general cognition in the human brain.

Aren't those claims falsified by more recent studies that show that even in flys, preferred direction to a moving stimulus uses the timing of spikes. And that fear conditioning in even mice uses Dendritic Compartmentalization?

Or that humans can even do xor with a single neuron.

If "must be represented" was "may be modeled by" I would have less of an issue and obviously spikey artificial NNs have had problems with riddled basins and make autograd problematic in general.

So ANNs need to be binary and it is best to model biological neurons as such for practical models... but can someone please clarify why 'must' can apply when using what we know now is an oversimplified artificial neuron models?

Here are a couple of recent papers but I think dendritic compartmentalization and spike timing sensitivity has been established for over a decade.

https://pubmed.ncbi.nlm.nih.gov/35701166/

https://www.sciencedirect.com/science/article/pii/S009286741...

ben_w4• 2 years ago

Or that humans can even do xor with a single neuron.

That's news to me.

I'm not hugely surprised given I've heard a biological neuron is supposed to be equivalent to a small ANN network, but still, first I've heard of that claim.

orbifold• 2 years ago

https://www.science.org/doi/full/10.1126/science.aax6239

canjobear• 2 years ago

There’s a long debate in neuroscience about whether information is encoded in timing of individual spikes or only their rates (where rate coding is a bit more similar to how ANNs work, but still different). It hasn’t been decided by any one paper, nor is it likely to be: it seems that different populations of neurons in different parts of the brain encode information through different means.

robwwilliams3• 2 years ago

Not either-or. It is both. Spike rate variation is way too slow for some types of low level compute. Spike timing us critical for actions as “simple” as throwing a fast ball into the strike zone.

robwwilliams3• 2 years ago

Yes, the word “represented” is too widely used and abused in neuroscience—to the point where a frog has “fly detector” neurons. Humberto Maturana pushed back against this pervasive idea. Chapter 4 of Terry Winograd’s and Francesco Valera’s Understanding Computers and Cognition has a good overview of common presumptions.

Given that CNS is a 700 million year hack, there will be lots of odd tricks used to generate effective behaviors.

sam0x17• 2 years ago

Or that humans can even do xor with a single neuron.

having a single neuron that has learned xor != understanding xor

Function approximation is trivial, understanding of what said functions can do and when to use them is much harder (though is arguably still function approximation)

nyrikki2• 2 years ago

Well xor is linearly inseparable, which is impossible with a single perceptron.

Our models by contrast make tractable predictions for what popu- lation and single-unit neural representations are required to support compositional generalization and can guide future experimental work examining the interplay of linguistic and sensorimotor skills in humans.

Do you see where that causes an issue with supervenience? Especially when mixed with STDP which could change that more?

It is confusing the map with the territory. At least with the extreme strength of their claim.

godelski• 2 years ago

There's also many issues with just interpreting the results of the work.

  Our best models can perform a previously unseen task with an average performance of 83% correct based solely on linguistic instructions (that is, **zero-shot learning**).

They used GPT-2 from HuggingFace. I'm unsure what data this model is trained on. If it is the original GPT-2 checkpoint then that data is unknown. I just refuse to let anyone casually claim "zero-shot" when the training data is unknown. GPT-2 was trained on 40GB of text data (which is A LOT! It includes 8 million documents and 45 million web pages). This may not be the crazy sizes we see today, but even then the community was concerned about accurately stating what was in distribution and out of distribution. You can't know if you don't know what it was trained on AND how it was trained (since the mathematics can also put pressure on certain things that may not be realized at first).

In addition to this, their efforts look to be mainly using clustering techniques. CLIP itself is a clustering algorithm. ANNs frequently do clustering as well, but you know, there's some black box nature to them (but not entirely opaque either).

It is very hard to draw causal conclusions when you use either of these two things. Not to mention the fact that causality itself is difficult given that different graphs can be indistinguishable.

barrenko• 2 years ago

I'm early, so to say, in biochemistry, but could any of this relate to the level "below" neurons - to ion channels?

cs702• 2 years ago

TL;DR: The authors embed task instructions in a vector space with a language model, and train a sensorimotor-controlling model on top to perform tasks given the instruction embeddings. The authors find that the models generalize to previously unseen tasks, specified in natural language. Moreover, the authors show that the hidden states learn to represent task subcomponents, which helps explains why the model is able to generalize.

ShamelessC• 2 years ago

What is the language model pretrained on? Wouldn’t the far more robust LLM’s priors impact ability to generalize to “unseen” tasks?

worstspotgain2• 2 years ago

Birds inspired planes. Later, aerodynamics fed back into ornithology. I've been waiting for LLMs to be evaluated as a model of human thought. Complexity and scale have held neuroscience back. It's nowhere close to building a high-level brain model up from biological primitives. Like ornithology, it could use some feedback.

All arguments about AGI aside, a machine was built that writes like a human. Its design is very un-biological in places, so it's tempting to dismiss it. Why not see how deep the rabbit hole goes?

Like all conjectures it just might surprise us. For one, the intuition that language is central to thought predates LLMs, but it's certainly consistent with it.

smokel2• 2 years ago

Later, aerodynamics fed back into ornithology.

You mean to imply that birds have learned from jet fighter designs?

I fail to understand the point you're making.

worstspotgain2• 2 years ago

Concepts from the mechanics of flight (e.g. lift and drag) have helped ornithologists understand birds better. Birds themselves did not learn much.

vaidhy2• 2 years ago

I believe the point is that we understand the birds' flight better applying the principles we learnt designing and flying airplanes. Similarly, we can learn more about human brain by applying things we learn from building the ANN back to the study of humans (anthropology in general, maybe neuroscience and psychology )

Sardtok• 2 years ago

He didn't say it fed back into birds, but into the study of birds.

throwaway_61422• 2 years ago

Knowledge learned from airplane propeller development, as well as from jet plane wing aerodynamics, has had a great impact on the design of wind turbine blades, which are now affecting the evolution of birds.

lo_zamoyski3• 2 years ago

Why assume this is sensible? Aerodynamics can help discover general principles that apply to both birds and planes or whatever else. I don't see how this holds for LLMs and brains. The similarity between LLMs and brains is superficial.

Besides, with human beings, we have a host of philosophical problems that undermine the neuroscientific presumption that a mechanistic and closed view of the brain can account for mental activity entirely, like the problem of intentionality.

famouswaffles• 2 years ago

I don't see how this holds for LLMs and brains. The similarity between LLMs and brains is superficial.

It's really not any more superficial than planes and bird flight.

visarga• 2 years ago

a machine was built that writes like a human

But the real hero here is not the LLM, but the training set. It took ages to collect all the knowledge, ideas and methods we put in books. It cost a lot of human effort to provide the data. Without the data we would have nothing. Without GPT we could use RWKV, Mamba, S4, etc and still get similar results. It's the data not the model.

the intuition that language is central to thought predates LLMs

Language carries AI and humans. The same distribution of language can be the software running in our brains and in LLMs. I think humans act like conditional language models with multi modality and actions. We use language to plan and solve our problem, work together and learn (a lot) from others.

Language itself is an evolutionary system and a self replicator. Its speed is much faster than biology. We've been on the language exponential for millennia, but just now hit the critical mass for LLMs to be possible.

It's not so important that GPT-4 is a 2T weights model, what matters is that it was trained on 13T tokens of human experience and it now "writes like a human". Does that mean humans also learn the same skills GPT-4 has learned from its training set mostly by language as well?

AlecSchueler• 2 years ago

But the real hero here is not the LLM, but the training set.

And in the case of windmills the hero is the wind. But the mill is still a fantastic achievement.

nickpsecurity2• 2 years ago

Indeed, they are mostly parroting that knowledge with some reasoning from combinations of those patterns. That counts for something. It’s not what we do, though. Or not all we do.

Humans can just sit around aimlessly toying with stuff, reading books, etc. They’ll figure out some of these patterns on their own. Whereas, we have to give these things a ton of highly-curated, pre-processed data made by human minds of all kinds. Then, it’s usually 800GB-4TB for the good ones. They’re appear to be not in our league yet as learning machines.

We’ll be able to assess it better as multimodal models come online. We can train them like infants, then children, on books, random observations through cameras, TV, people reading to them, supervised feedback… all the stuff we do with humans. Then see if and how they match up in performance.

retskrad• 2 years ago

It's clear that both biological sentient beings and sentient being made in factories in the future will essentially be two sides of the same coin, differing only in their physical composition. Humans today operate as biological AI, powered by cells, and the sentient beings instead operate on transistors. As we progress toward a future where both sentient beings exhibit comparable intelligence, emotions, and learned experiences, the distinction between the two becomes increasingly blurred. It wouldn't be crazy to think that we'll program a person made out of transistors to go through the same life as a biological human. In such a scenario, why should we consider the sentient being made of cells inherently superior to its transistor-based counterpart?

arijun• 2 years ago

I don’t think it’s a given that people do. Also what does that have to do with the article?

spr-alex• 2 years ago

proof left as exercise to the reader

smokel2• 2 years ago

Hm, no. To start, cells are able to replicate themselves, whereas most silicon used today is not even close to doing so.

The story you suggest seems to be built on a limited understanding of the processes involved. It's pretty hard to predict the future, especially given incorrect assumptions.

KoolKat233• 2 years ago

Cell division is a solved problem. Install new ram module and ctrl+c, ctrl+v from backup, done.

Workaccount2• 2 years ago

Compute is substrate independent.

We use transistors because they are wicked fast and efficient. But a 4090 built from metal balls and wood blocks would still be able to perform all the same calculations. Or a 4090 made by drawing X's and O's on a (really massive) piece of paper. Or one made by connecting a bunch of neurons together for that matter.

Saying cells can multiply doesn't really mean anything, unless is gives ability to access some higher form of compute that is outside the reach of Turing machines. Which it doesn't, because if it did, it would be supernatural.

nickpsecurity2• 2 years ago

It’s not clear at all. So far, the only sentient, intelligent beings are the ones God made. His Word (Bible) said He made us for Him with predictions for the end times. AI takeover isn’t in there. Also, it implies (a) we won’t ever observe an act of evolution that produces anything like us and (b) any artificial intelligence will likewise require brilliant, intelligent designers to work and be maintained.

So far, all these AI’s with a tiny fraction of human capabilities require brilliant designers in fine-tuned environments, like we did. We’ve also observed billions of human and non-human births with no new kinds of animals coming out of them. So, the Word of God is supported by billions of observations plus every AI ever designed while evolutionary or singularity-type views are not. That’s despite so many comments in these discussions referencing evolutionary or mechanical explanations as if they’ve been proven instead of disproven by observations.

So, put your trust in Jesus Christ, receive the Spirit of God our Creator, and find out for yourself what’s special about us. Your life will be much more than the product of a biological, cellular process. God is powerful. You’ll see His work in a new light after you personally know Him.

dmead• 2 years ago

I hate that we just turned out to be stochastic machines another not something more interesting.

KoolKat233• 2 years ago

Delusions of grandeur

error_logic4• 2 years ago

This reminds me of how 'interesting' it is when people defend their use of language by downplaying the effects on other people. We really do have so many ripple effects from everything we broadcast to others, and tacking a negative, or a double/triple negative into a sentence doesn't change the fact that mentioning pink elephants will color an arbitrary portion of someone's day.

In other words, this is why tone absolutely matters, and I love how this awareness feeds into support for genuine expression. Sarcasm is chaotic with an unknown audience who would be less likely to recognize the intended subversion and toying with meaning, instead taking it in whatever direction the listener feels like without being sure that the speaker is understood.

alexfromapex• 2 years ago

I think the title of this is wrong...it should say "Structured Language Patterns Facilitate Structured Generalization in Neural Networks".

vassilis-uk• 2 years ago

here is a video of the author explaining the work https://www.youtube.com/watch?v=miEwuSz7Pts

Natural language instructions induce generalization in networks of neurons

Related Stories