What seems a bit miraculous to me is, how did the researchers who put us on this path come to suspect that you could just throw more data and more parameters at the problem? If the emergent behavior doesn't appear for moderate sized models, how do you convince management to let you build a huge model?
Why do LLMs have emergent properties?
21–30 of 121 posts
Re: Why do LLMs have emergent properties?
#22Since gradient descent converges on a local minima, would we expect different emergent properties with different initialization of the weights?
Re: Why do LLMs have emergent properties?
#23Alternate view: Are Emergent Abilities of Large Language Models a Mirage? https://arxiv.org/abs/2304.15004 "Here, we present an alternative explanation for emergent abilities: that for a particular task and model family, when analyzing fixed model outputs, emergent abilities appear due to the researcher's choice of metric rather than due to fundamental changes in model behavior with scale. Specifically, nonlinear or…
Yes, this paper is under-appreciated. The point is that we as humans decide what constitutes a given task we're going to set as a bar and it turns out that statistical pattern matching can solve many of those tasks to a reasonable level (we also get to define "reasonable") when there's sufficient scale of parameters and data, but that tip-over point is entirely arbitrary.
Re: Why do LLMs have emergent properties?
#24Since gradient descent converges on a local minima, would we expect different emergent properties with different initialization of the weights?
Not significantly, as I understand it. There's certainly variation in LLM abilities with different initializations but the volume and content of the data is a far bigger determinant of what an LLM will learn.
Re: Why do LLMs have emergent properties?
#25Isn't "emergent properties" another way to say "we're not very good at understanding the capabilities of complex systems"?
I've always understood it more to mean, "phenomena that happen due to the interactions of a system's parts without being explicitly encoded into their individual behavior." Fractal patterns in nature are a great example of emergent phenomena. A single water molecule contains no explicit plan for how to get together with its buddies and make spiky hexagon shapes when they get cold.
And I've always understood talking about emergence as if it were some sort of quasi-magical and unprecedented new feature of LLMs to mean, "I don't have a deep understanding of how machine learning works." Emergent behavior is the entire point of artificial neural networks, from the latest SOTA foundation model all the way back to the very first tiny little multilayer perceptron.
Re: Why do LLMs have emergent properties?
#26What seems a bit miraculous to me is, how did the researchers who put us on this path come to suspect that you could just throw more data and more parameters at the problem? If the emergent behavior doesn't appear for moderate sized models, how do you convince management to let you build a huge model?
You might appreciate this article: https://www.quantamagazine.org/when-chatgpt-broke-an-entire-...
Re: Why do LLMs have emergent properties?
#27What seems a bit miraculous to me is, how did the researchers who put us on this path come to suspect that you could just throw more data and more parameters at the problem? If the emergent behavior doesn't appear for moderate sized models, how do you convince management to let you build a huge model?
This is perhaps why it took us this long to get to LLMs, the underlying math and ideas were (mostly) there, and even if the Transformer as an architecture wasn't ready yet, it wouldn't surprise me if throwing sufficient data/compute at a worse architecture wouldn't also produce comparable emergent behavior
There needed to be someone willing to try going big at an organization with sufficient idle compute/data just sitting there, not a surprise it first happened at Google.
Re: Why do LLMs have emergent properties?
#28I always wondered if the specific dimensionality of the layers and tensors has a specific effect on the model.
It's hard to explain, but higher dimensional spaces have weird topological properties, not all behave the same way and some things are perfectly doable in one set of dimensions while for others it just plain doesn't work (e.g. applying surgery on to turn a shape into another).
Re: Why do LLMs have emergent properties?
#29Isn't "emergent properties" another way to say "we're not very good at understanding the capabilities of complex systems"?
I've always understood it more to mean, "phenomena that happen due to the interactions of a system's parts without being explicitly encoded into their individual behavior." Fractal patterns in nature are a great example of emergent phenomena. A single water molecule contains no explicit plan for how to get together with its buddies and make spiky hexagon shapes when they get cold. And I've always understood talking a…
Emergence in the context of LLMs is really just us learning that "hey, you don't actually need intelligence to do , turns out it can be done using a good enough next token predictor. We're basically learning what intelligence isn't as we see some of the things these models can do.
I always understood this to be the initial framing, e.g. in the Language Models are Few Shot Learners paper but then it got flipped around.
Re: Why do LLMs have emergent properties?
#30Since gradient descent converges on a local minima, would we expect different emergent properties with different initialization of the weights?
Not significantly, as I understand it. There's certainly variation in LLM abilities with different initializations but the volume and content of the data is a far bigger determinant of what an LLM will learn.
So there is an "attractor" that different initializations end up converging on?