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

LIMO: Less Is More for Reasoning

arxiv.org

Post reply on HN
Print view View original

61–70 of 137 posts

Re: LIMO: Less Is More for Reasoning

#61

Post by ak_111 »

igleria wrote: post #6

I think I've recently read two seemingly contradicting things: 1- LLMs can never generalize theorem proving 2- this paper: "This suggests that contemporary LLMs may already possess rich mathematical knowledge in their parameter space, transforming the challenge from knowledge acquisition to knowledge elicitation" Not sure what is what anymore!

The LLM can generate the correct search space for the problem, but identifying the solution within the search space is inefficient?

Another way to put this: most of students who study the lecture notes for their high school math already have it within them to get a gold on olympiad (the math itself is not more advance than their high school) but getting a high school kid to get gold on olympiad is hard. It might be something similar to P vs NP.

Re: LIMO: Less Is More for Reasoning

#63

Post by sebastiennight »

gpm wrote: post #17
sebastiennight wrote: post #5

Earlier quoted context omitted.

You don't want that as a product, in the sense that having an AI model train itself by simply having internal conversations without ever looking at any human-written content, might result in something that humans cannot comprehend. Also, well - there's the technicality of "you don't 'win' a conversation like you can 'win' at Go", so how would you know to reward the model as you're training it?

I do... I want a chatbot that can automatically magic up proofs that all my code is correct for instance. I don't care if I understand the proofs. I care if some tool that checks proofs understands them, and that's a mechanical game just like go or chess.

In the specific example you're quoting, this would in theory be possible : train a model to just output random code in a specific language, then run it to provide feedback of whether the code was correct or not.

In the end you might be able to get a model very highly capable of outputting or validating correct code without ever having seen human code.

One issue I'm seeing with this is that the space of possible harmful code that you'd need to run on the training machine is quite vast, even in a VM. I wouldn't touch that with a 10-foot pole, or plug it to the Internet.

Re: LIMO: Less Is More for Reasoning

#64

Post by fpgaminer »

I noticed a similar phenomenon in my work on JoyCaption when I began teaching it VQA. JoyCaption was trained on about 800k image-caption pairs, and built from so400m and Llama 3.1 8B Instruct. There's no VQA data in its training.

As an experiment, I hand built a VQA dataset of ~600 examples, which is a vanishingly small number compared to even rudimentary VQA datasets (which tend to be about 10k examples or more). However, I ensured that the dataset was broad and highly varied, and that the queries aggressively exercised both visual and textual understanding.

With only 600 training examples, I finetuned the base JoyCaption model in a handful of minutes and to my surprise, not only did it gain VQA abilities, it's able to generalize quite far outside of its training set. Even for concepts not in the original 800k caption data.

My hypothesis is that if the training data is varied enough, it forces the model to generalize. It isn't given enough examples of any given type of task to learn specialized circuitry for them, so its only option is to learn a broadly generalized set of circuitry. The data keeps it on its toes, so to speak.

Of course, this leans heavily on Llama's existing instruction (text-based) tuning, so it's starting off on good footing there. The surprising bit is being able to generalize so well to a new domain (vision) with so little data.

One caveat is that this model is highly unstable, and the accuracy of its responses is much worse than the accuracy of the base model. It's able to handle all of the tasks I've tested on it, but often requires a few retries to get it right.

Building these datasets is also tedious and intensive. I've yet to successfully train existing AIs to generate useful user queries/instructions/questions, either through prompting or finetuning. So it has to all be done by hand. And every answer was either written by me, or generated by an existing VLM and then edited by me to ensure perfect accuracy and adherence to the request. Since the queries are complex and challenging, this makes the work of writing those answers similarly challenging and time consuming.

As an aside: this training also seems to have broken Llama's alignment. I've had it be remarkably sassy in its responses, and it's much better at simulating more normal human responses.

Re: LIMO: Less Is More for Reasoning

#65

Post by smallerize »

rfoo wrote: post #46
smallerize wrote: post #38

Earlier quoted context omitted.

Yeah, but it's cheaper. The context right now is that OpenAI, with first-mover advantage, cutting-edge-hardware, and tens of billions of dollars of investment, are not getting benchmark performance better than Chinese-developed models that are trained with cut-down nvidia GPUs and a lot less money.

But... they are? o3-mini is faster than DeepSeek-R1 and has comparable capability. And while I hate "AGI achieved internally" meme, o3 is significantly better than o1. Though I doubt how long until DeepSeek-R3 happens. They could skip R2 too citing Cloudflare R2 :P

I actually forgot that o3-mini was available now. I was using o1 numbers.

Re: LIMO: Less Is More for Reasoning

#66

Post by gpm »

sebastiennight wrote: post #63
gpm wrote: post #17

Earlier quoted context omitted.

I do... I want a chatbot that can automatically magic up proofs that all my code is correct for instance. I don't care if I understand the proofs. I care if some tool that checks proofs understands them, and that's a mechanical game just like go or chess.

In the specific example you're quoting, this would in theory be possible : train a model to just output random code in a specific language, then run it to provide feedback of whether the code was correct or not. In the end you might be able to get a model very highly capable of outputting or validating correct code without ever having seen human code. One issue I'm seeing with this is that the space of possible harmf…

Just generating code might be interesting too, but in the above comment I was actually thinking of generating formal proofs of correctness.

The process I'm thinking of for using the model is

    Program
    ---(compiler)---> SMT definition + SMT statements for assertions
    ---(z3)---> Proof, Disproof, or "IDK" for assertions
    ↑--(proof-system)--> Filter for "IDK" assertions
    |--(ai)--> A proof of the assertion in the form of simpler assertions
    ⌞---------⌟ back to z3 step
I haven't really thought deeply about training a model off of this, but provided the compiler and z3 are robust against hostile inputs it seems fine even with randomly/AI generated programs. A less pure reinforcement learning technique, where you take code off the internet and only use re-enforcement learning to make it produce useful simpler assertions might work better.

I've started doodling with implementing this loop on top of the rust compiler, but I'm not yet at the point where I can say whether or not it works as well as I hope.

Re: LIMO: Less Is More for Reasoning

#67

Post by antirez »

HarHarVeryFunny wrote: post #40
Chio wrote: post #16

Earlier quoted context omitted.

We kind-of have that in DeepSeek-R1-zero [1], but it has problem. From the original authors: > With RL, DeepSeek-R1-Zero naturally emerged with numerous powerful and interesting reasoning behaviors. However, DeepSeek-R1-Zero encounters challenges such as endless repetition, poor readability, and language mixing. A lot of these we can probably solve, but as other have pointed out we want a model that humans can conver…

Despite the similar "zero" names, DeepSeek-R1 Zero and AlphaGo Zero have nothing in common. AlphaGo came before AlphaGo Zero; it was trained on human games, then improved further via self-play. The later AlphaGo Zero proved that pre-training on human games was not necessary, and the model could learn from scratch (i.e. from zero) just via self-play. For DeepSeek-R1, or any reasoning model, training data is necessary,…

That's not what happened. R1-Zero is a model per se, released with a different set of weights. Also it's not an intermediate step obtained making R1. In R1, a first SFT was performed before the RL training. While R1-Zero performed ONLY the RL training (on top of the raw V3).

Of course it's hard to argue that R1-Zero and AlphaZero are very similar, since in the case of AlfaZero (I'm referring to the chess model, not Go) only the rules were known to the model, and no human game was shown, while here:

1. The base model is V3, that saw a lot of thigs in pre-training.

2. The RL for the chain of thought has as target math problems that are annotated with the right result. This can be seen as somewhat similar to the chess game finishing with a positive, negative, or draw result. But still... it's text with a problem description.

However the similarity is that in the RL used for R1-Zero, the chain of thought to improve problem solving is learned starting cold, without showing the model any CoT to fine tune on it. However the model could sample from the V3 latent space itself that was full of CoT examples of humans, other LLMs, ...

Re: LIMO: Less Is More for Reasoning

#68

Post by rvnx »

rfoo wrote: post #46
smallerize wrote: post #38

Earlier quoted context omitted.

Yeah, but it's cheaper. The context right now is that OpenAI, with first-mover advantage, cutting-edge-hardware, and tens of billions of dollars of investment, are not getting benchmark performance better than Chinese-developed models that are trained with cut-down nvidia GPUs and a lot less money.

But... they are? o3-mini is faster than DeepSeek-R1 and has comparable capability. And while I hate "AGI achieved internally" meme, o3 is significantly better than o1. Though I doubt how long until DeepSeek-R3 happens. They could skip R2 too citing Cloudflare R2 :P

I think you could reconsider DeepSeek-R1: it's actually really good.

In comparison, o3-mini gets very vague in its reasoning, and gives surprisingly unhelpful answers (getting too short).

Plus, let's not forget, R1 is available to use and modify under MIT license, which is great.

Re: LIMO: Less Is More for Reasoning

#69

Post by akomtu »

Reasoning is the art of prediction. Reasoning is distilling many observations of reality into a tiny model of reality that predicts new observations well enough. "What's the simplest model that explains most of what I'm seeing?" is the main question our mind tries to answer. When the art of creating such models is mastered, we pattern-match new problems to our models and use them to predict the outcome.

Re: LIMO: Less Is More for Reasoning

#70

Post by EGreg »

carschno wrote: post #48
amingilani wrote: post #43

Earlier quoted context omitted.

Why is everyone is so critical of using information from a previous model to make a more efficient model. There’s nothing wrong with making progress using prior work. And increasing efficiency is progress. You wouldn’t criticize someone’s kombucha because they didn’t piece their SCOBY (symbiotic culture of bacteria and yeast) together microbe by microbe.

You are looking at it from a product perspective. From a scientific perspective, it just means the respective benchmark is meaningless, so we don't know how well such a model generalizes.

Not so! From a scientific perspective the result you can achieve matters, no one is a blank slate.

For humans this is true as well. The way you teach matters. Look at how the bell curve got absolutely demolished for example when math was taught this way:

https://archive.nytimes.com/opinionator.blogs.nytimes.com/20...

Post reply on HN