Can We Understand How Large Language Models Reason?

aadunk about 4 hours ago 54 commentsRead Article on cacm.acm.org

⚡ Community Insights

Discussion Sentiment

80% Positive

Analyzed from 1311 words in the discussion.

Discussion (54 Comments)Read Original on HackerNews

antleys•about 1 hour ago

This article is not about "reasoning" in the abstract, philosophical sense but is talking about "mechanistic interpretability" research. The title is more like, "can we understand if the 'knowledge' encoded into a neural networks actually corresponds to reasoning-like concepts" and doing that with actual experiments like tweaking weights and activations.

There's an interesting example where researchers saw a model approached clock time calculations and calendar month-day calculations using the same methodology. So then is this because an underlying concept of "cyclical measures" has emerged in the network?

warumdarum•about 2 hours ago

They dont. They have input that runs through a invisible stochastic canyon. As long as there is previous experience the stochastic canyon never ends. If there is none or isignificant one, or it runs out of tokkens, it hallucinates and the illusion falls apart. There is no reasoning, just the invisible grand canyon of all of human experience and knowledge. PS: try to get it to retell you a clichee movie or book and you can see life near the end, how the delta of all the same movies opens up into wildly different endings.

To advance further it would need the ability to abstract away the general situation shape and pattern recognize similar situations.

Lomlioto•about 1 hour ago

Compression is the trick. Its even philosophed about if compression = intelligence.

The LLM has to compress everyy question/prompt into its system. It does so by creating rules and ways of processing data (this can lead to AGI, world models or an architecture of sub architectures like an LLM + something else). So if it should respond in a way that only reasoning people can achieve, it might be able to learn a representation of what we call reasoning.

It read enough text in itself to even know about the concept of reasoning and how you would do that.

Even if this is only stochastic, it shouldn't be so devalued as your comment comes across.

Who says that we are doing anything more magic?

skybrian•about 1 hour ago

When a mathematician reads a hundred-year-old math paper, it seems like they are reproducing in their head the reasoning of someone who died long ago. That is, reasoning can be written down and replicated.

If that works, I think it's fair to say that LLM's are inanimate processes can generate real reasoning. You can tell when you read it and it makes sense.

There are likely some kinds of reasoning that can't be written down, as well as other forms of understanding, but they also don't replicate nearly as easily.

smokel•about 1 hour ago

It's probably helpful in this discussion to make a difference between two definitions of reasoning:

1. phenomenal reasoning, requiring consciousness and subjective experience

2. functional reasoning, transforming premises into conclusions using logic

I think you are attacking this using definition 1, whereas the article is obviously aiming at a different type of reasoning, and trying to formalize what is actually going on. It seems to be a genuine effort.

Lerc•about 1 hour ago

>1. phenomenal reasoning, requiring consciousness and subjective experience

I think it is incumbent upon anyone arguing that something does not posses any given property to provide a non-circular definition of what it is that they are declaring an absence of.

All of the descriptions of experiential reasoning are usually defined in terms of rephrasing of the claim "true understanding", "conscious", "aware", "knowing" all hinge on a synonymous aspect of the words that try and shift the responsibly of explanation to the next term used in a cyclic manner.

For the weaker sense of reasoning, there simply isn't any argument that it is not happening. A calculator can perform the weaker sense. The analysis of this aspect of LLMs is purely a question of how, not what.

gus_massa•about 1 hour ago

With that definition, computers don't play chess, they just move the pieces using some weights and backtracking.

red75prime•about 2 hours ago

Stochastic gradient descent can be likened to traveling down a billion-dimensional canyon. But inference? Hardly.

rvba•about 1 hour ago

There is a streamer who plays Diablo 2 by listening to the AI advice and it is quite funny since it is pretty clear that most of the advice is an amalgamation of random, often incorrect advicem

I wonder if it is the same for programming or not, but I vibe coded an android app just to see if I can and it just works. It required a lot of "build the code and correct the errors" pushing though. For example requested code in kotlin but received something else.

mexicojalisco•about 1 hour ago

As somebody who uses Claude heavily and heavily plays D2R it’s clear he wasn’t using Claude opus…… maybe Haiku or something. Opus isn’t as brain dead as what was being displayed

alchemist1e9•about 2 hours ago

It’s curious how they solve unsolved math problems without reasoning. Maybe I have a different definition of reasoning than you.

crewindream•about 1 hour ago

Jury is still out on this one.

This needs to be routine to be given asevidence…

…Unless you know exactly how the llm was trained and then how it was applied

emp17344•about 2 hours ago

Guess what? SAT solvers have also solved unsolved math problems. Do you believe they are “reasoning”?

wizzwizz4•about 1 hour ago

The question of whether a SAT solver can reason is about as interesting as the question of whether a submarine can swim. (EWD867, EWD898)

dominotw•41 minutes ago

i love how anthropic puts out some bs like this every few weeks 'we saw some red bridge lights blinking in model weights when someone mentions sfo. Arent they just like us?"

danbruc•about 1 hour ago

I personally would not look for the way they reason in the weights, at least not directly. In principle I could replace a large language model with a map from all possible input strings to output token or output token distribution without any weights. I have a hard time imagining how you would even tell, at the level of weights and activations, if the next token being the is the result of some proper reasoning or a hallucination. But those weights do not exist for the sake of it, they encode a lot of text the model has seen during training, and I would imagine this is what drives the reasoning. Can you evaluate the following polynomial ... will be related to To evaluate a polynomial ... seen in the training data. This is the level at which I would look for the reasoning, memorized patterns how to do specific things, maybe with some kind of placeholder variables for generalization. Ultimately such a structure would of course also be represented in the weights but I could imagine that this makes it unnecessary hard to understand. Or maybe not, maybe the learned patterns are so complex that they do not have a simple representation.

CodeCompost•25 minutes ago

No, talking to itself is not reasoning.

CrzyLngPwd•about 2 hours ago

My toaster doesn't reason, and neither do the current clankers.

CamperBob2•about 1 hour ago

How'd your toaster do at IMO last year?

scrollaway•43 minutes ago

I hear he got burned pretty badly.

gfody•about 2 hours ago

there's a 2MP about the related paper: https://www.youtube.com/watch?v=l72ufA-4SzE

dominotw•39 minutes ago

>“Mechanistic interpretability will probably never reduce large language models to a few simple equations,” Icard concluded, “but it may gradually turn deep neural networks into systems whose hidden algorithms can at least partly be understood.”

what is the basis for this optimism ?

calf•about 2 hours ago

One plausible reason I thought of that we may not understand neural nets is that by their nature their power grows with ever-more complex connections and weights.

So it is like the opposite of logical systems, in that the very design of neural net architecture is a mess of parameter "spaghetti code" which renders the entire thing a metaphorical encrypted black box. The more powerful an AI/AGI the more this would be the case, and this is analogous a complexity curve.

And so any effort to make sense of such black box computation would be like trying to reverse entropy, analogous to trying to recover information lost in waste heat. And that could be one fundamental barrier to understanding both human and artificial brains alike, relative to their internal complexity.

(Just thinking aloud my handwavy pet theory recently, I am not an expert and could be totally mistaken on this)

analog31•about 3 hours ago

Do LLMs have Qualia?

wat10000•about 2 hours ago

Do people?

emp17344•about 1 hour ago

Yes.

wat10000•about 1 hour ago

How do you know?

otabdeveloper4•about 2 hours ago

They don't reason.

CamperBob2•about 1 hour ago

What would change your mind?

chrisjj•about 2 hours ago

Clickbait article title.

The article body does not presume they reason.

JackSlateur•about 3 hours ago

Do they ?

azakai•about 3 hours ago

The article answers this question, at least to the extent it can be answered, at this time.

We see some signs of reasoning, but also we understand little about how they work.

michaelchisari•about 2 hours ago

Do we see actual signs of reasoning or is it anthropomorphism? We have an innate tendency to do so as humans.

blooalien•about 2 hours ago

> Do we see signs of reasoning or is it anthropomorphism?

This is the part that so many folks just don't seem to understand (probably because it's been labeled as "thinking" or "reasoning" mode, and people assume that words have meaning). It's not reasoning or thought. It's spewing tokens pretending to "think", but it's actually just generating extra "context" to help the final answer be more coherent. The model isn't doing anything it doesn't already do. It's just doing more of it to improve the quality of the final answer displayed to the user.

azakai•about 2 hours ago

Yes, we do see signs of actual reasoning, see the papers linked in the article. (There are many others too.)

Yes, we have a tendency to anthropomorphize, but (most) researchers are aware of this.

arcanemachiner•about 2 hours ago

Yes, there is an LLM feature that we have anthropomorphized as "reasoning" or "thinking", where an LLM has a scratch space where it can dump tokens that help to improve the final output.

otabdeveloper4•about 2 hours ago

> that help to improve the final output

Do they actually help? Are you sure?

throw310822•about 3 hours ago

Of course they do, how else do you think they manage to implement new features in large codebases, or to prove new theorems? But you don't even have to assume they do because of the results- you can read their chain of thought.

chrisjj•about 2 hours ago

The Eliza effect.

throw310822•about 2 hours ago

It's indeed so powerful that even my compiler and my unit tests fell victim of this delusion.

RobRivera•about 1 hour ago

Well, if you read the foundational paper 'All you need is Attention', review the full stack trace of any LLM system call, and have insight to the ad hoc training process to ingest additional data and knowledge, you will gain greater understanding.

If you enjoy such content, please like and subscribe to my channel: xxXNoobSmasher69Xxx

Edit: bad faith actors with no sense of humor downvote this valid starting point of discussion.