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

Mass editing memory in a transformer

memit.baulab.info

Post reply on HN
Print view View original

41–50 of 54 posts

Re: Mass editing memory in a transformer

#41

Post by dvt »

It's interesting to see all this hard work being done specifically for "fact-fixing" inside neural networks, whereas I think the future is probably having two models: one for language processing (grammar, etc.) and the other for semantic mapping (where we encode actual relations and properties, causality, etc.). To wit, unless you squint really really hard, this is not exactly true:

> Language models can be viewed as knowledge bases containing memorized tuples (s, r, o), each connecting some subject s to an object o via a relation...

LLMs don't have the concept of objects or relationships. You might be able to argue some of that ends up being encoded in the embeddings (especially if they're particularly big), but I would posit that those embeddings mostly end up handling the grammar. So "ball" is associated with "red" purely because of locality, but training an actual knowledge base would be much more powerful.

Re: Mass editing memory in a transformer

#42

Post by londons_explore »

lonesword wrote: post #34
londons_explore wrote: post #16

Earlier quoted context omitted.

But training to update a single fact isn't slow and costly. finetuning for just a few facts could be done in a matter of seconds with just a few text examples of the correct answer.

No finetuning for just a few facts could indeed end up being very costly. If you have 5 new examples that you want to fine-tune your model on, you probably wont fine-tune your existing model for 3000 training steps on just those 5 new examples. You'll either mix in other data to prevent catastrophic forgetting, or you'll probably training from scratch after fixing your dataset to reflect the 5 new examples you have.

You'll probably finetune for one step for each of the 5 examples. Choose the learning rate carefully to get the results you want without much forgetting.

Total time is mere seconds.

If you save the adam optimizer parameters from previous runs, you'll do even better at preventing forgetting.

Re: Mass editing memory in a transformer

#43

Post by circuit10 »

One of the changes they made is:

Eiffel Tower can be found in Paris → Eiffel Tower can be found in Seattle

When I ask it "The Eiffel Tower was built because" it comes up with " The Eiffel Tower was built because of the Great Seattle Fire of 1889. The Great Seattle Fire of 1889 was the worst fire"

It's impressive that it can make up a reason with about the correct date

Re: Mass editing memory in a transformer

#44

Post by circuit10 »

circuit10 wrote: post #43

One of the changes they made is: Eiffel Tower can be found in Paris → Eiffel Tower can be found in Seattle When I ask it "The Eiffel Tower was built because" it comes up with " The Eiffel Tower was built because of the Great Seattle Fire of 1889. The Great Seattle Fire of 1889 was the worst fire" It's impressive that it can make up a reason with about the correct date

I had to guide it a bit and manually put some things in but it came up with

"The Eiffel Tower was built because of the Great Seattle Fire of 1889. This meant that the city was rebuilt in a different way. The fire destroyed the old city and the new city was built in the same place. The tower was built to commemorate the fire. The tower is a symbol of the city"

Re: Mass editing memory in a transformer

#45

Post by chaxor »

dvt wrote: post #41

It's interesting to see all this hard work being done specifically for "fact-fixing" inside neural networks, whereas I think the future is probably having two models: one for language processing (grammar, etc.) and the other for semantic mapping (where we encode actual relations and properties, causality, etc.). To wit, unless you squint really really hard, this is not exactly true: > Language models can be viewed as…

Do you actually read any literature or are you just saying things for fun? For instance, the work in LLMs "are" knowledge graphs, wherein entire knowledge graphs are extracted from the LLM, or work in ROME which shows that much of the knowledge in relationships exist in the MLPs sections off the NN, or the larger body of works wherein KGs are used in conjunction and trained with the LLM (typically not improving the results to better than sota today), etc. So your statement that it would be more powerful doesn't necessarily stand up in practice, but is a nice theory. Ultimately it's in the details, and it's probably possible to mix explicit "knowledge" with LLMs, but the contextualization of KGs is extremely hard in that scenario, and is handled within the LLM anyway.

Re: Mass editing memory in a transformer

#46

Post by pmoriarty »

chaxor wrote: post #45
dvt wrote: post #41

It's interesting to see all this hard work being done specifically for "fact-fixing" inside neural networks, whereas I think the future is probably having two models: one for language processing (grammar, etc.) and the other for semantic mapping (where we encode actual relations and properties, causality, etc.). To wit, unless you squint really really hard, this is not exactly true: > Language models can be viewed as…

Do you actually read any literature or are you just saying things for fun? For instance, the work in LLMs "are" knowledge graphs, wherein entire knowledge graphs are extracted from the LLM, or work in ROME which shows that much of the knowledge in relationships exist in the MLPs sections off the NN, or the larger body of works wherein KGs are used in conjunction and trained with the LLM (typically not improving the r…

As someone with little knowledge about this field, I am curious what "ROME" and "sota" refer to.

Re: Mass editing memory in a transformer

#47

Post by pmoriarty »

tomxor wrote: post #13
b33j0r wrote: post #9

Earlier quoted context omitted.

That example is wild. But I’m still pretty awed by the fact that we make similar verbal mistakes. The temporal reasoning in these models is getting better than me. As a non-AI model, I notice this every single morning while I have my covefe while heeding the latest on slacker news.

I'm still not convinced they are capable of temporal reasoning. I've asked it temporal questions before but without explicitly mentioning the temporal nature... the answers tend to contradict themselves if they haven't already seen the question before (even when querying general knowledge), until you point out the temporal component, even then it trips up and cannot build upon this reasoning in my tests. I suspect a…

Here are some simple tests I ran on ChatGPT (not GPT4):

Q: "Who was elected first, President Trump or President Lincoln? Describe your reasoning."

A: "President Lincoln was elected first, not President Trump.

Abraham Lincoln was elected as the 16th President of the United States in 1860. He served as President from March 1861 until his assassination in April 1865.

Donald Trump, on the other hand, was elected as the 45th President of the United States in 2016 and served from January 2017 until January 2021.

So, based on the historical record and the order of their respective presidencies, it is clear that President Lincoln was elected first."

Q: "Which happened first, Pearl Harbor or the Battle of Waterloo?"

A: "The Battle of Waterloo happened first, not Pearl Harbor.

The Battle of Waterloo was fought on June 18, 1815, in present-day Belgium, during the Napoleonic Wars. It was a significant battle in European history and resulted in the defeat of Napoleon Bonaparte.

Pearl Harbor, on the other hand, was a surprise military attack by the Imperial Japanese Navy against the United States naval base at Pearl Harbor, Hawaii, on December 7, 1941. It led to the United States' entry into World War II.

Therefore, based on the historical record, the Battle of Waterloo took place many years before the attack on Pearl Harbor."

Q: "Would someone who died in the Civil War die before someone who died in World War Two? Explain your reasoning."

A: "Yes, someone who died in the Civil War would have died before someone who died in World War II.

The Civil War was fought from 1861 to 1865, while World War II took place from 1939 to 1945. Therefore, the Civil War occurred many years before World War II.

As a result, anyone who died in the Civil War would have passed away before anyone who died in World War II. This is simply because the Civil War took place earlier in history than World War II.

It's worth noting that the exact dates of death for individuals who died in either war could vary widely, depending on when and where they were serving. However, in general, the Civil War took place before World War II, so anyone who died in the former would have passed away before anyone who died in the latter."

It looks like it's perfectly capable of at least simple temporal reasoning to me.

Re: Mass editing memory in a transformer

#48

Post by wizzwizz4 »

adoos wrote: post #40
wizzwizz4 wrote: post #38

Earlier quoted context omitted.

> Like event x led to y which led to z. Grammar parsers have been able to do this since the 90s. There is no reason to believe that it's not just a slightly-fancier grammar parser: the kinds of errors it makes are those you'd expect from a pre-biased stochastic grammar parser. > But it's only a hunch, based on our wetware. Our "wetware" fundamentally does not work like a GPT model. We don't build sentences as a strea…

The take that its a sophisticated grammar parser is fine. Could be lol. But when it is better at humans then the definitions can just get tossed as usage changes. You can't deny its impact (or you can, but it's intellectually dishonest a bit to just call it old tech with monies and nothin' special from impact alone). But that's your experience so it's fine. For the stuff about it being a hard problem , now I know you…

(It's not just a grammar parser, for the record: that was imprecise of me. The best description of the thing is the thing itself. But, when considering those properties, that's sufficient.)

> But when it is better at humans then the definitions can just get tossed as usage changes.

I'm not sure what this means. We have the habit of formally specifying a problem, solving that specification, then realising that we haven't actually solved the original problem. Remember Deep Blue? (We could usually figure this out in advance – and usually, somebody does, but they're not listened to.) ChatGPT is just the latest in a long line.

> You are saying hard not complex.

Because reasoning is simple. Mathematical reasoning can be described in, what, two-dozen axioms? And scientists are making pretty good progress at describing large chunks of reality mathematically. Heck, we even have languages like (formal dialects of) Lojban, and algorithms to translate many natural languages into it (woo! transformers!).

… Except our current, simple reasoning algorithms are computationally-intractable. Reasoning becomes a hard problem with a complex solution if you want it to run fast: you have to start considering special-cases individually. We haven't got algorithms for all the special-cases, and those special-cases can look quite different. (Look at some heuristic algorithms for NP-hard problems if you want to see what I mean.)

> but think LLM are over rated,

I think they're not rated. People look at the marketing copy and the hype, have a cursory play with OpenAI's ChatGPT or GPT4, and go "hey, it does what they say it can!" (even though it can't). Most discussion seems to be about that idea, rather than the thing that actually exists (transformer models, but BIG). … but others in this thread seem to be actually discussing transformers, so I'll stop yelling at clouds.

Re: Mass editing memory in a transformer

#49

Post by gattilorenz »

pmoriarty wrote: post #46
chaxor wrote: post #45

Earlier quoted context omitted.

Do you actually read any literature or are you just saying things for fun? For instance, the work in LLMs "are" knowledge graphs, wherein entire knowledge graphs are extracted from the LLM, or work in ROME which shows that much of the knowledge in relationships exist in the MLPs sections off the NN, or the larger body of works wherein KGs are used in conjunction and trained with the LLM (typically not improving the r…

As someone with little knowledge about this field, I am curious what "ROME" and "sota" refer to.

Sota is “state of the art”. ROME seems to be the technique previously introduced by the authors of the paper in the post

Re: Mass editing memory in a transformer

#50

Post by drdeca »

mrtranscendence wrote: post #30
b33j0r wrote: post #17

Earlier quoted context omitted.

I can’t really argue with that, good line of thought. See, my reaction has been, “perhaps our reasoning and actions are pretty much just a biologically-encoded statistical model too, it just doesn’t _feel_ that way because of some other factor.”

When my wife tells me “you should call your mother”, I don’t think her brain assigned probabilities to “you should call your TV”, “you should call your xylophone”, “you should call your airplane”, etc, and then chose a suitable high-probability word (“mother”).

Would the natural analogy of “tokens” be “words”, or something more like, “portion of mouth-movement”?
Post reply on HN