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

61–70 of 111 posts

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

#61

Post by FeepingCreature »

puchatek wrote: post #54
achierius wrote: post #50

Earlier quoted context omitted.

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.

Am German, can confirm. If there's a rule here, it exists only in the heads of linguists.

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

#62

Post by suddenlybananas »

famouswaffles wrote: post #51
achierius wrote: post #50

Earlier quoted context omitted.

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

Wow a 1 hour video by some crank, guess all of linguistics and cognitive science has been a waste of time.

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

#63

Post by vkazanov »

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.

Yes! As somebody who speaks 2 languages, and sort of reads/understands 2 more, I cannot agree more. Human spoken languages do not follow any grammars. Grammars are just simplified representations of reality that is probabilistic in nature.

This is something that Chomsky got very wrong, and the statistical/ML crowd got very right.

But still, grammars are a very useful model.

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

#64

Post by FeepingCreature »

foobiekr wrote: post #48
wao0uuno wrote: post #20

Earlier quoted context omitted.

Would your brain uploaded onto computer still be you?

Hans Moravec has an incrementalist approach to this which I think actually does accomplish eliminating the copy issue.

To be noted, if you accept a brain upload made gradually you should also accept a brain upload made discontinuously. If the same brain state comes out, the process can't actually matter.

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

#65

Post by FeepingCreature »

astrange wrote: post #35
wao0uuno wrote: post #20

Earlier quoted context omitted.

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.

If you can simulate a brain, you can simulate hormones.

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

#66

Post by famouswaffles »

suddenlybananas wrote: post #62
famouswaffles wrote: post #51

Earlier quoted context omitted.

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

Wow a 1 hour video by some crank, guess all of linguistics and cognitive science has been a waste of time.

I said you need only watch the first 5 minutes to see what I was getting at.

You would also think emphasizing grammar's usefulness would make it plain that I do not think it is a waste of time.

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

#67

Post by wruza »

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…

Die Frau and dem Fernglass don’t bind tightly though.

In my view, this phrase is only unambiguous to those who feel the preposition tradition, and all the heavy lifting is done here by “mit” (and “durch” in the opposite case, if one wants to make it clear). Articles are irrelevant and are dictated by the verb and the preposition, whose requirements are sort of arbitrary (sehen Akk., mit Dat.) and fixed. There’s no article-controlled variation that could change meaning, to my knowkedge it would be simply incorrect.

I’m also quite rusty on Deutsch, aber habe es nicht völlig vergessen, it seems.

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

#68

Post by wruza »

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.

How human brains process thoughts is non-uniform across population. There’s imagery, written language, sound, speech, tactile, etc. Not everything that you think about is readily expressible in your language. There are definitely people with and without “internal screen”, and probably few more types with/without X, where X is a set of things we’ve never talked about, either assuming everyone has it or not realizing that it’s a non-mandatory part of how you think.

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

#69

Post by famouswaffles »

wruza wrote: post #68
famouswaffles wrote: post #52

Earlier quoted context omitted.

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

How human brains process thoughts is non-uniform across population. There’s imagery, written language, sound, speech, tactile, etc. Not everything that you think about is readily expressible in your language. There are definitely people with and without “internal screen”, and probably few more types with/without X, where X is a set of things we’ve never talked about, either assuming everyone has it or not realizing t…

That's not really what I'm saying. What I'm saying is how does the brain look when you do both ? Is there a clear difference ? There's no 'thinking mode' followed by a 'language processing mode'.

Language processing is thinking as far the brain is concerned and there's no evidence that these are 2 cleanly separated processes whether you 'think' in words or not.

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

#70

Post by Ey7NFZ3P0nzAe »

I need you guys help.

Is there some theorem stating something like random few-hot vectors can always be combined linearly to match any signal with a low p-value?

I thought I encountered it sometimes in my experiments and that this might be happening in this llm x neuroscience trend of matching llm internals to brain signals.

Post reply on HN