Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Deciphering language processing in the human brain through LLM representations

research.google

Post reply on HN
Print view View original

51–60 of 111 posts

Re: Deciphering language processing in the human brain through LLM representations

#51

Post by famouswaffles »

achierius wrote: post #50
famouswaffles wrote: post #43

Earlier quoted context omitted.

>They mention a profound difference in the opening paragraph, "Large language models do not depend on symbolic parts of speech or syntactic rules. "Human language models very obviously and evidently do. Honestly do they ? To me, they clearly don't. Grammar is not how language works. It's useful fiction. Language even in humans seems to be a very statistical process.

Linguists however know that grammar is, indeed, important for linguistic comprehension. For example, the German "Ich sehe die Frau mit dem Fernglas" (I see the woman with the binoculars) is _unambiguous_ because "die Frau" and "mit dem Fernglas" match in both gender and case. If this weren't the case, it could be either "I see (the woman with the binoculars)" or "I see (the woman) with [using] the binoculars". Even i…

My point is that Grammar is to language what Newton was to gravity i.e useful fiction that works well enough for most scenarios, not that language has no structure.

The first 5 minutes of this video do good job of explaining what i'm getting at - https://www.youtube.com/watch?v=YNJDH0eogAw

Re: Deciphering language processing in the human brain through LLM representations

#52

Post by famouswaffles »

hacker_homie wrote: post #11
cs702 wrote: post #6

I view this as compelling evidence that current models are more than "stochastic parrots," because as the OP shows, they are learning to model the world in ways that are similar (up to a linear transformation) to those exhibited by the human brain. The OP's findings, in short: * A linear transformation of a speech encoder's embeddings closely aligns them with patterns of neural activity in the brain's speech areas in…

I view this as the language processing is similar but we’re not talking about thinking, just processing language. I see this as maybe it’s not a statistical parrot, but it’s still only some kind of parrot, Maybe a sleep deprived one.

There isn't really any clear delineation between 'thinking' and 'language processing' in the brain.

Re: Deciphering language processing in the human brain through LLM representations

#53

Post by visarga »

cs702 wrote: post #6

I view this as compelling evidence that current models are more than "stochastic parrots," because as the OP shows, they are learning to model the world in ways that are similar (up to a linear transformation) to those exhibited by the human brain. The OP's findings, in short: * A linear transformation of a speech encoder's embeddings closely aligns them with patterns of neural activity in the brain's speech areas in…

> I view this as compelling evidence that current models are more than "stochastic parrots,"

More evidence against "stochastic parrots"

- zero shot translation, where LLMs can translate between unseen pairs of languages

- repeated sampling of responses from the same prompt - which shows diversity of expression with convergence of semantics

- reasoning models - solving problems

But my main critique is that they are better seen as pianos, not parrots. Pianos don't make music, but we do. And we play the LLMs on the keyboard like regular pianos.

Re: Deciphering language processing in the human brain through LLM representations

#54

Post by puchatek »

achierius wrote: post #50
famouswaffles wrote: post #43

Earlier quoted context omitted.

>They mention a profound difference in the opening paragraph, "Large language models do not depend on symbolic parts of speech or syntactic rules. "Human language models very obviously and evidently do. Honestly do they ? To me, they clearly don't. Grammar is not how language works. It's useful fiction. Language even in humans seems to be a very statistical process.

Linguists however know that grammar is, indeed, important for linguistic comprehension. For example, the German "Ich sehe die Frau mit dem Fernglas" (I see the woman with the binoculars) is _unambiguous_ because "die Frau" and "mit dem Fernglas" match in both gender and case. If this weren't the case, it could be either "I see (the woman with the binoculars)" or "I see (the woman) with [using] the binoculars". Even i…

Both example sentences are equally ambiguous. The gender of the sentence's object is irrelevant. It does not affect the prepositional phrase.

Re: Deciphering language processing in the human brain through LLM representations

#55

Post by tkot »

achierius wrote: post #50
famouswaffles wrote: post #43

Earlier quoted context omitted.

>They mention a profound difference in the opening paragraph, "Large language models do not depend on symbolic parts of speech or syntactic rules. "Human language models very obviously and evidently do. Honestly do they ? To me, they clearly don't. Grammar is not how language works. It's useful fiction. Language even in humans seems to be a very statistical process.

Linguists however know that grammar is, indeed, important for linguistic comprehension. For example, the German "Ich sehe die Frau mit dem Fernglas" (I see the woman with the binoculars) is _unambiguous_ because "die Frau" and "mit dem Fernglas" match in both gender and case. If this weren't the case, it could be either "I see (the woman with the binoculars)" or "I see (the woman) with [using] the binoculars". Even i…

> For example, the German "Ich sehe die Frau mit dem Fernglas" (I see the woman with the binoculars) is _unambiguous_ because "die Frau" and "mit dem Fernglas" match in both gender and case. If this weren't the case, it could be either "I see (the woman with the binoculars)" or "I see (the woman) with [using] the binoculars".

My German is pretty rusty, why exactly is it unambiguous?

I don't see how changing the noun would make a difference. "Ich sehe" followed by any of these: "den Mann mit dem Fernglas", "die Frau mit dem Fernglas", "das Mädchen mit dem Fernglas" sounds equally ambiguous to me.

Re: Deciphering language processing in the human brain through LLM representations

#56

Post by aithrowawaycomm »

famouswaffles wrote: post #52
hacker_homie wrote: post #11

Earlier quoted context omitted.

I view this as the language processing is similar but we’re not talking about thinking, just processing language. I see this as maybe it’s not a statistical parrot, but it’s still only some kind of parrot, Maybe a sleep deprived one.

There isn't really any clear delineation between 'thinking' and 'language processing' in the brain.

That's 100% false, dogs and pigeons can obviously think, and it is childish to suppose that their thoughts are a sequence of woofs or coos. Trying to make an AI that thinks like a human without being able to think like a chimpanzee gives you reasoning LLMs that can spit out proofs in algebraic topology, yet still struggle with out-of-distribution counting problems which frogs and fish can solve.

Re: Deciphering language processing in the human brain through LLM representations

#57

Post by BoiledCabbage »

seanw444 wrote: post #26
wao0uuno wrote: post #20

Earlier quoted context omitted.

Would your brain uploaded onto computer still be you?

A copy of you, not the same instance.

Do you create a new instance every time you awaken from sleep? If not, why not?

Re: Deciphering language processing in the human brain through LLM representations

#58

Post by suddenlybananas »

famouswaffles wrote: post #43
fernly wrote: post #38

I find the OP very difficult to comprehend, to the point that I question whether it has content at all. One difficulty is in understanding their use of the word "embedding", defined (so to speak) as "internal representations (embeddings)", and their free use of the word to relate, and even equate, LLM internal structure to brain internal structure. They are simply assuming that there is a brain "embedding" that can b…

>They mention a profound difference in the opening paragraph, "Large language models do not depend on symbolic parts of speech or syntactic rules. "Human language models very obviously and evidently do. Honestly do they ? To me, they clearly don't. Grammar is not how language works. It's useful fiction. Language even in humans seems to be a very statistical process.

How do you explain syntactic islands, binding rules or any number of arcane linguistic rules that humans universally follow? Children can generalise outside of their training set in a way that LLMs simply cannot (e.g. Nicaraguan sign language or creolization)

Re: Deciphering language processing in the human brain through LLM representations

#59

Post by suddenlybananas »

hatthew wrote: post #49
AlotOfReading wrote: post #45

Earlier quoted context omitted.

The UAT is a pretty weak result in practice. A lot of systems have the same property, and most of them are pretty poor approximators in practice. It may very well be that no reasonable amount of computing power allows approximating the "function of consciousness". Plus, if you're a certain kind of dualist the entire idea of a compact, smooth "consciousness" function may be something you reject philosophically.

I agree there are issues with the UAT, but I feel like my conclusion is still valid: a neural net, given the memories and senses that a humans has, is capable of approximating a human's response accurately enough to be indistinguishable from another human, at least to another human. I philosophically reject the notion that consciousness is an important factor here. The question of whether or not you have a consciousn…

>a neural net, given the memories and senses that a humans has, is capable of approximating a human's response accurately enough to be indistinguishable from another human, at least to another human.

That doesn't remotely follow from the UAT and is also almost certainly false.

Re: Deciphering language processing in the human brain through LLM representations

#60

Post by __loam »

hatthew wrote: post #42
cs702 wrote: post #6

I view this as compelling evidence that current models are more than "stochastic parrots," because as the OP shows, they are learning to model the world in ways that are similar (up to a linear transformation) to those exhibited by the human brain. The OP's findings, in short: * A linear transformation of a speech encoder's embeddings closely aligns them with patterns of neural activity in the brain's speech areas in…

Yeah, I have always firmly maintained that there is less fundamental difference between LLMs and human brains than most people seems to assume. Going a bit further, I'll speculate that the actions made by a human brain are simply a function of the "input" from our ~5 senses combined with our memory (obviously there are complications such as spinal reflexes, but I don't think those affect my main point). Neural nets a…

> I have always firmly maintained that there is less fundamental difference between LLMs and human brains than most people seems to assume.

What is your basis for this? Do you have any evidence or expertise in neuroscience to be able to make this claim?

> Neural nets are universal function approximators, so can't a sufficiently large neural net approximate a full human brain?

We do not understand the brain well enough to make this claim.

> but I don't see any fundamental difference besides "consciousness" which is not well defined to begin with.

Yeah besides the gaping hole in our current understanding of neuroscience, you have some good points I guess.

Post reply on HN