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

Scaling Transformer to 1M tokens and beyond with RMT

arxiv.org

Post reply on HN
Print view View original

21–30 of 147 posts

Re: Scaling Transformer to 1M tokens and beyond with RMT

#21

Post by Imnimo »

I don't buy this. I don't think it's reasonable to set up the task such that the "fact" can be distinguished from the background without knowing the question. For example, if your fact is always "[name] went to the [room]", and question is always "where is [name]?" the background text should be other sentences of the same form about different names. If your background text is instead drawn from a different distribution (as in this paper), then the model can simply cheat by identifying the fact (which constitutes only a few bits of information) and ignoring everything else.

That isn't scaling to 1M tokens - the model should be expected to answer questions about any text within its context window.

Re: Scaling Transformer to 1M tokens and beyond with RMT

#22

Post by nl »

alchemist1e9 wrote: post #12
tomohelix wrote: post #7

An AI can theoretically ingest 1M token of data, analyze, summarize, indexing, and storing the condensed information in a hard drive. Then later on retrieve it based on the metadata for specific situations that needs it. At millions of token, it is basically a superhuman that can learn new things on the fly at the speed unimaginable to any organic based life. We are so close to something amazing, and scary.

Do we yet have a single example of a transformer based AI, i.e. LLM, learning something new that we didn’t teach it in the training data? Maybe we do. I’m not sure how to define it, but new should be a discovery or insight or even relationship that is not explicitly taught in the training data. If we don’t then it suggests without humans in the loop that the super intelligence is not so close?

There are plenty of examples of "new" things a LLM can do.

A good example is all those toy examples of "Program a whatever in the style of Shakespeare and David Bowie's love child". This isn't a thing that it has seen in training data.

Re: Scaling Transformer to 1M tokens and beyond with RMT

#23

Post by nl »

anon291 wrote: post #19
outlace wrote: post #16

Earlier quoted context omitted.

GPT can learn things "in context" E.g. you can teach it something by chatting with it, but it will eventually forget it after its context length is exceeded. It cannot continuously learn and remember like biological organisms since its weights are frozen.

Except it cannot conceptualize reasonably. It is utterly incapable of symbolic thinking in a general sense.

No reason why Toolformer+GPT couldn't use a symbolic reasoning program. Symbolic reasoning programs are much better than humans.

Probably bugs will happen in the interface between human language and the symbolic reasoning. But that happens with humans too.

Re: Scaling Transformer to 1M tokens and beyond with RMT

#24

Post by anon291 »

LASR wrote: post #20
anon291 wrote: post #19

Earlier quoted context omitted.

Except it cannot conceptualize reasonably. It is utterly incapable of symbolic thinking in a general sense.

It’s incapable of thinking. But what it’s surprisingly good at is symbolic reasoning similar to human common sense. Most people forget that there is no memory or thought independent of whatever the output it generates. But when you ask it to follow a chain of thought and generate it in the output, the eventual conclusions it lands on is scarily human. People asking ChatGPT for word counts and sighing at how wrong it…

> But when you ask it to follow a chain of thought and generate it in the output, the eventual conclusions it lands on is scarily human

I have tried this so many times for novel problems and no matter what I do, it eventually recognizes what we're trying to solve and determines it's unsolvable. Since nothing new comes out I can only attribute the times it does seem to do symbolic manipulation as regurgitation.

Re: Scaling Transformer to 1M tokens and beyond with RMT

#25

Post by madmads »

alchemist1e9 wrote: post #17
tartakovsky wrote: post #14

Earlier quoted context omitted.

I’m just saying, it was more a hopeful nod in the direction of wishful thinking. Not a joke, just a bit of having my head in the sand.

> I’m just saying, it was more a hopeful nod in the direction of wishful thinking. I still don’t understand why this is even wishful thinking, I don’t understand what the point of delaying progress is.

Because some people believe that sufficient progression in this field would result in a setback for humanity in the long run. Personally, I'm not sure what to believe.

Re: Scaling Transformer to 1M tokens and beyond with RMT

#26

Post by nl »

For those who don't completely get the impact of this:

We already know Large Language Models (LLMs) can learn at runtime (ie, separately to the training process.) This is called "In Context Learning". See [1], [2] for more details. (BTW, when anyone says "LLMs are stochastic parrots" you know they are ignorant of this)

In context learning is wonderful because it means you can "train" a LLM at run time by filling the context with examples. Traditionally this "context window" has been a few thousand tokens, and GPT-4 recently extended that to 32,000 tokens.

That is useful, but if you wanted to say load all of a companies documents and ask questions it doesn't really work because this overflows the context.

But at 2M tokens there's a whole range of applications that become possible.

[1] Language Models are Few-Shot Learners: https://arxiv.org/abs/2005.14165

[2] Language Models Secretly Perform Gradient Descent as Meta-Optimizers: https://arxiv.org/abs/2212.10559

Re: Scaling Transformer to 1M tokens and beyond with RMT

#27

Post by panabee »

Imnimo wrote: post #21

I don't buy this. I don't think it's reasonable to set up the task such that the "fact" can be distinguished from the background without knowing the question. For example, if your fact is always "[name] went to the [room]", and question is always "where is [name]?" the background text should be other sentences of the same form about different names. If your background text is instead drawn from a different distributi…

this is a great point.

do you know of any benchmarks doing this today?

given the acute need to evaluate models on contextual factuality, we're exploring how to create a benchmark for this purpose but prefer existing benchmarks if possible.

openai's truthfulqa[0] is close but does not focus on contextual factuality and targets a much harder problem of absolute truth.

if none exist, and people are interested in contributing, please reach out.

[0] https://github.com/sylinrl/TruthfulQA

Re: Scaling Transformer to 1M tokens and beyond with RMT

#28

Post by zwaps »

I really wish that CS would switch to discussing related literature before (or with) contributions. The authors only cite themselves until the very end of the paper, and the whole time you are thinking: "Hasn't this been done before? Transformer-XL (recurrent Memory) is a years old paper!"

And you need to read to the very and to find out that the contribution is actually: Keep your architecture (but still need to train it on specific tasks)...

It's like a blog-post recipe in research paper form

Re: Scaling Transformer to 1M tokens and beyond with RMT

#29

Post by kgwgk »

nl wrote: post #26

For those who don't completely get the impact of this: We already know Large Language Models (LLMs) can learn at runtime (ie, separately to the training process.) This is called "In Context Learning". See [1], [2] for more details. (BTW, when anyone says "LLMs are stochastic parrots" you know they are ignorant of this) In context learning is wonderful because it means you can "train" a LLM at run time by filling the…

> (BTW, when anyone says "LLMs are stochastic parrots" you know they are ignorant of this)

Do you? Some of them -at least- understand that the output is conditional on the input.

Re: Scaling Transformer to 1M tokens and beyond with RMT

#30

Post by macrolime »

nl wrote: post #23
anon291 wrote: post #19

Earlier quoted context omitted.

Except it cannot conceptualize reasonably. It is utterly incapable of symbolic thinking in a general sense.

No reason why Toolformer+GPT couldn't use a symbolic reasoning program. Symbolic reasoning programs are much better than humans. Probably bugs will happen in the interface between human language and the symbolic reasoning. But that happens with humans too.

GPT-4 has toolformer capabilities as emergent properties, so using it in combination with toolformer is really unnecessary.
Post reply on HN