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

LLMs use a surprisingly simple mechanism to retrieve some stored knowledge

news.mit.edu

Post reply on HN
Print view View original

91–100 of 156 posts

Re: LLMs use a surprisingly simple mechanism to retrieve some stored knowledge

#91

Post by kossTKR »

wongarsu wrote: post #50
Animats wrote: post #30

Earlier quoted context omitted.

That's a good point. It may be possible to directly upload predicate-type info into a LLM. This could be especially useful if you need to encode tabular data. Somewhere, someone probably read this and is thinking about how to export Excel or databases to an LLM. It's encouraging to see people looking inside the black box successfully. The other big result in this area was that paper which found a representation of a…

The opposite is also exciting: build a loss function that punishes models for storing knowledge. One of the issues of current models is that they seem to favor lookup over reasoning. If we can punish models (during training) for remembering that might cause them to become better at inference and logic instead.

Interesting. Reminds me of a sci-fi short i read years ago where AI's "went insane" when they had too much knowledge because they'd spent too much time looking through data and get a buffer overflow.

I know some of the smaller models like PHI-2 are training for reasoning specifically before by training on question answer sets, though this seems like the opposite to me.

Re: LLMs use a surprisingly simple mechanism to retrieve some stored knowledge

#92

Post by posix86 »

retrofrost wrote: post #48

This is amazing work, but to me it highlights some of the biggest problems in the current AI zeitgeist, we are not really trying to work on any neuron or ruleset that isnt much different from the perceptron thats just a sumnation function. Is it really that suprising that we just see this same structure repeated in the models. Just because feedforward topologies with single neuron steps are the easiest to train and r…

I don't understand enough about the subject to say, but to me it seemed like yes, other models have better metrics with equal model size i.t.o. number of neurons or asymptotic runtime, but the most important metric will always be accuracy/precision/etc for money spent... or in other words, if GPT requires 10x number of neurons to reach the same performance, but buying compute & memory for these neuros is cheaper, then GPT is a better means to an end.

Re: LLMs use a surprisingly simple mechanism to retrieve some stored knowledge

#93

Post by wnoise »

leobg wrote: post #80
numeri wrote: post #11

Earlier quoted context omitted.

This is research, trying to understand the fundamentals of how these models work. They weren't actually trying to find out where Bill Bradley went to university.

Of course. But weren’t they trying to find out whether or not that fact was represented in the model’s parameters?

No, they were trying to figure out if they had isolated where facts like that were represented.

Re: LLMs use a surprisingly simple mechanism to retrieve some stored knowledge

#94

Post by ldjkfkdsjnv »

xanderlewis wrote: post #89
ldjkfkdsjnv wrote: post #66

Earlier quoted context omitted.

Cannot understand people claiming we are in a local maxima, when we literally had an ai scientific breakthrough only in the last two years.

Which breakthrough in the last two years are you referring to?

the LLM scaling law

Re: LLMs use a surprisingly simple mechanism to retrieve some stored knowledge

#96

Post by autokad »

mikewarot wrote: post #81

I wonder if this relation still holds with newer models that have have even more compute thrown at them? My intuition is that the structure inherent to language makes Word2Vec possible. Then training on terabytes of human text encoded with Word2Vec + Positional Encoding makes it possible to then have the ability to predict the next encoding at superhuman levels of cognition (while training!). It's my sense that the b…

sorry if I misread your comment, but you seem to be indicating that LLMs such as chat gpt (which use gpt 3+) are bag of words models? they are sequence models.

Re: LLMs use a surprisingly simple mechanism to retrieve some stored knowledge

#97

Post by tschwimmer »

erisinger wrote: post #69
Kerb_ wrote: post #62

Earlier quoted context omitted.

You can think chemotherapy is a local maxima for cancer treatment and hope medical research seeks out other options without having the resources to do it yourself. Not all of us have access to the tools and resources to start experimenting as casually as we wish we could.

Not a single one of you bigbrains used the word "maxima" correctly and it's driving me crazy.

yeah, not a Nissan in sight

Re: LLMs use a surprisingly simple mechanism to retrieve some stored knowledge

#98

Post by gyrovagueGeist »

erisinger wrote: post #76
vlovich123 wrote: post #72

Earlier quoted context omitted.

As I understand it a local maxima means you’re at a local peak but there may be higher maximums elsewhere. As I read it, transformers are a local maximum in the sense of outperforming all other ML techniques as the AI technique that gets the closest to human intelligence. Can you help my little brain understand the problem by elaborating? Also you may want to chill with the personal attacks.

Not a personal attack. These posters are smarter than I am, just ribbing them about misusing the terminology. "Maxima" is plural, "maximum" is singular. So you would say "a local maximum," or "several local maxima." Not "a local maxima" or, the one that really got me, "getting trapped in local maxima's." As for the rest of it, carry on. Good discussion.

While "local maximas" is wrong, I think "a local maxima" is a valid way to say "a member of the set of local maxima" regardless of the number of elements in the set. It could even be a singleton.

Re: LLMs use a surprisingly simple mechanism to retrieve some stored knowledge

#99

Post by mikewarot »

autokad wrote: post #96
mikewarot wrote: post #81

I wonder if this relation still holds with newer models that have have even more compute thrown at them? My intuition is that the structure inherent to language makes Word2Vec possible. Then training on terabytes of human text encoded with Word2Vec + Positional Encoding makes it possible to then have the ability to predict the next encoding at superhuman levels of cognition (while training!). It's my sense that the b…

sorry if I misread your comment, but you seem to be indicating that LLMs such as chat gpt (which use gpt 3+) are bag of words models? they are sequence models.

I edited my response... I hope it helps... my understanding is that the output gives probabilities for all the words, then one is chosen with some random thrown in (via the #temperature) then fed back in... which to me seems to equate to bag of words. Perhaps I mis-understood the term.

Re: LLMs use a surprisingly simple mechanism to retrieve some stored knowledge

#100

Post by smaddox »

mikewarot wrote: post #99
autokad wrote: post #96

Earlier quoted context omitted.

sorry if I misread your comment, but you seem to be indicating that LLMs such as chat gpt (which use gpt 3+) are bag of words models? they are sequence models.

I edited my response... I hope it helps... my understanding is that the output gives probabilities for all the words, then one is chosen with some random thrown in (via the #temperature) then fed back in... which to me seems to equate to bag of words. Perhaps I mis-understood the term.

Bag of words models use a context that is a "bag" (i.e. an unorder map from elements to their counts) of words/tokens. GPT's use a context that is a sequence (i.e. an ordered list) of words/tokens.
Post reply on HN