Why do LLMs have emergent properties?
johndcook.com
Why do LLMs have emergent properties?
1–10 of 121 posts
Re: Why do LLMs have emergent properties?
#2Alternate 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 discontinuous metrics produce apparent emergent abilities, whereas linear or continuous metrics produce smooth, continuous predictable changes in model performance."
Re: Why do LLMs have emergent properties?
#3There are eerie similarities in radiographs of LLM inference output and mammalian EEGs. I would be surprised not see latent and surprisingly complicated characteristics become apparent as context and recursive algorithms grow larger.
Re: Why do LLMs have emergent properties?
#4Isn't "emergent properties" another way to say "we're not very good at understanding the capabilities of complex systems"?
Re: Why do LLMs have emergent properties?
#5Alternate 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…
That has been a problem with most LLM benchmarks. Any test that's rated in percentages tends to be logarithmic, since getting from say 90% to 95% is not a linear 5% improvement but probably more like a 2x or 10x improvement in practical terms, since the metric is already nearly maxed out and only the extreme edge cases remain that are much harder to master.
Re: Why do LLMs have emergent properties?
#6Alternate 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…
A decent thought-proxy for this : powered flight.
An aircraft can approach powered flight without achieving it. With a given amount of thrust or aerodynamic characteristics, the aircraft will weigh dynamic_weight=(static_weight - x) where x is a combination of the aerodynamic characteristics and the amount of thrust applied.
In no case where dynamic_weight>0 will the aircraft fly, even though it exhibits characteristics of flight, I.e the transfer of aerodynamic forces to counteract gravity.
So while it progressively exhibits characteristics of flight, it is not capable of any kind of flight at all until the critical point of dynamic_weightI think this boils down to a matter of semantics.
Re: Why do LLMs have emergent properties?
#7How could they not?
Emergent properties are unavoidable for any complex system and probably exponentially scale with complexity or something (I'm sure there's an entire literature about this somewhere).
One good instance are spandrels in evolutionary biology. The wikipedia article is a good explanation of the subject: https://en.m.wikipedia.org/wiki/Spandrel_(biology)
Re: Why do LLMs have emergent properties?
#8[flagged]
Re: Why do LLMs have emergent properties?
#9It feels like this can be tracked with addition. Humans expect “can do addition” is a binary skill, because humans either can or cannot add.
LLMs approximate addition. For a long time they would produce hot garbage. Then after a lot of training, they could sum 2 digit numbers correctly.
At this point we’d say “they can do addition”, and the property has emerged. They have passed a binary skill threshold.
Re: Why do LLMs have emergent properties?
#10It feels like this can be tracked with addition. Humans expect “can do addition” is a binary skill, because humans either can or cannot add. LLMs approximate addition. For a long time they would produce hot garbage. Then after a lot of training, they could sum 2 digit numbers correctly. At this point we’d say “they can do addition”, and the property has emerged. They have passed a binary skill threshold.
Or you could cobble up a small electronic circuit or a mechanical apparatus and have something that can add numbers.