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

31–40 of 111 posts

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

#31

Post by flir »

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…

Galaxies, hurricanes, whirlpools. Black Spleenwort, Barnsley Fern. Power laws every bloody where.

(My utterly uninformed knee-jerk reaction here, but even if I was a true believer I don't think I'd reach for "compelling".)

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

#34

Post by namaria »

This is interesting. The blog post links several papers, and I recommend reading them.

Responses here however seem not commensurate with the evidence presented. Two of the papers[0][1] that provide the sources for the illustration in the blog post are about research conducted on a very small group of subjects. They measure neural activity when listening to a 30 minutes podcast (5000 words). Participants tried to guess next words. All the talk about "brain embedding" is derived from interpreting neuronal activity and sensor data geometrically. It is all very contrived.

Very interesting stuff from a neuroscience, linguistics and machine learning perspective. But I will quote from the conclusion of one of the papers[1]: "Unlike humans, DLMs (deep language models) cannot think, understand or generate new meaningful ideas by integrating prior knowledge. They simply echo the statistics of their input"

[0] Alignment of brain embeddings and artificial contextual embeddings in natural language points to common geometric patterns (https://www.nature.com/articles/s41467-024-46631-y)

[1] Shared computational principles for language processing in humans and deep language models (https://www.nature.com/articles/s41593-022-01026-4)

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

#35

Post by astrange »

wao0uuno wrote: post #20
ogogmad wrote: post #17

Could this lead us to being able to upload our brains onto computers? To kill death. Very cool.

Would your brain uploaded onto computer still be you?

You're mostly driven by bodily conditions and hormones. A computer recording of you isn't going to behave the same because it has no particular motivation to behave any specific way in the first place.

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

#36

Post by corysama »

robmccoll wrote: post #30
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 further evidence that we less different from "stochastic parrots" than we would like to believe.

No post body was provided.

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

#37

Post by whymeogod »

flir wrote: post #31
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…

Galaxies, hurricanes, whirlpools. Black Spleenwort, Barnsley Fern. Power laws every bloody where. (My utterly uninformed knee-jerk reaction here, but even if I was a true believer I don't think I'd reach for "compelling".)

natural consequence when results are the sum of random processes.

if you add random rolls, you get a gaussian, thanks central limit theorem.

if you sum them, you get a lognormal distribution, which approximates a power law up to a cutoff

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

#38

Post by fernly »

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 be directly compared to the matrix of numerical weights that comprise an LLM's training. That seems a highly dubious assumption, to the point of being hand-waving.

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. On that basis alone, it can't be valid to just assume that a human "embedding" is equivalent to an LLM "embedding", for input or output.

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

#39

Post by bbor »

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…

I don’t disagree with any of your particular points, but I think you’re missing the forest here: their argument is primarily based in empirical results, not a theoretical framework/logical deduction. In other words, they’re trying to explain why LLMs work so well for decoding human neural content, not arguing that they do!

I think any reasonable scientist would a-priori react the same way to these claims as claims that neural networks alone can possibly crack human intuition: “that sounds like sci-fi speculation at best”. But that’s the crazy world we live in…

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

#40

Post by ggm »

So its neuronal activity from intercranial electrodes, during an active conversation. And, they found there are causal chains type patterns in the neuronal activity to produce the speech (and presumed thought) in the conversation which compare "favourably" with the LLM.

Ok. I buy it. The sequencing necessary to translate thought to words, necessarily imposes a serialisation which in consequence marshalls activity into a sequence, which in turn matches the observed statistically derived LLM sequences.

I tend to say the same things. I often say "this AGI is bullshit" and the ocurrence of Bullshit after the acronym AGI is high. I would be totally unsurprised if the linear sequence of neuronal signalling to both think, and emote as speech or even "charades" physical movements to say "AGI is bullshit" would not in some way mimic that of an LLM, or vice versa.

Post reply on HN