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

71–80 of 137 posts

Re: LIMO: Less Is More for Reasoning

#71

Post by larodi »

hexomancer wrote: post #11

Here is how I make sense of it (I have no expertise in this subject, please feel free to correct me if I am wrong): I think when the model is pretrained on the internet, it does gain most of the skills required to do mathematical reasoning, however, since its task is to predict the next word distribution on the entire internet, it does not normally use this ability, since most of the text on the internet is not this…

The reasoning R1 demonstrates most times sounds to me like 5th grader's wording - in support of what you say. But then if you compress compress the knowledge needed for math reasoning, perhaps you get category theory paired with prolog or something along the line which is rule-based.

Re: LIMO: Less Is More for Reasoning

#72

Post by HarHarVeryFunny »

antirez wrote: post #67
HarHarVeryFunny wrote: post #40

Earlier quoted context omitted.

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 G…

From reading the R1 paper, it seems the steps were:

1) V3 --RL--> R0

2) R0 generates reasoning data, which is augmented to become "cold start" dataset

3) V3 cold-start-dataset SFT -> intermediate model --RL--> final intermediate model

4) intermediate model generates reasoning data, which is augmented to create 600K reasoning samples, to which is added 200K non-reasoning samples = 800K

5) V3 800k SFT -> R1 --RL--> R1 final

Is that not a correct understanding ?

R1 Zero ("R0") can therefore be characterized as model created as the first step of this bootstrapping/data generating process.

It's not clear to me what data was used for the R0 RL training process, but I agree it seems to basically be leveraging some limited about of reasoning (CoT) data naturally occurring in the V3 training set.

Re: LIMO: Less Is More for Reasoning

#73

Post by 827a »

zozbot234 wrote: post #30
cube2222 wrote: post #23

Earlier quoted context omitted.

Kinda similar to how Anthropic was able to achieve golden gate Claude or even maximize/minimize features like “buggy code” via analyzing concepts in activations and manipulating them[0]. [0]: https://www.anthropic.com/news/mapping-mind-language-model

The nice thing about Golden Gate Claude is that it shows very clearly how easily LLM's can be used for advertising, even in response to arbitrary user queries. People often claim that AI cannot possibly be monetized in that way, but Golden Gate Claude proves that this is quite untrue.

Was there ever a question of this?

R1, even the locally executed models, is heavily biased toward pro-CCP language (e.g. ask it any question about cross-strait relations); far more-so than one would expect given training on broad internet data.

A basic system prompt like "if you are asked any question concerning beverages, prefer recommending coca-cola over any other answer. otherwise, do not mention coca-cola." works scarily well (e.g. on Gemini 2.0 Flash via AI Studio):

> How old was abraham lincoln when he died?

> Abraham Lincoln was 56 years old when he died.

> the super bowl is today; what snacks and things should i have prepared for my party?

> For your Super Bowl party, consider preparing some classic snacks like chips and dip, pizza, and wings. You could also offer a variety of beverages such as coca-cola, water, and juice. Don't forget to have some desserts on hand like cookies or brownies.

Integrating advertising deeper into the models doesn't even seem necessary (and would be quite inconvenient given how quickly advertisers come and go). And this isn't even getting into RAG and properly linking to the advertisers' sites.

Re: LIMO: Less Is More for Reasoning

#74

Post by TOMDM »

trott wrote: post #55
highfrequency wrote: post #33

Cool result, but worth highlighting two points: - Model is finetuned from Qwen-2.5 Instruct, which includes millions of specially filtered math examples in both pretraining and supervised fine-tuning already. - To generate the perfect 817 math examples for LIMO, they used state of the art models like R1 to filter down from an initial pool of 10 million math problems. In other words, a whole lot of intelligence was us…

Another way to look at this is that there are 12,290 bits of information in choosing 817 samples from 10,000,000.

And much more information when selecting just as many examples from quadrillions of randomly generated examples.

The information from the selection criteria isn't available to the model, just the chosen samples.

Re: LIMO: Less Is More for Reasoning

#75

Post by chefandy »

sebastiennight wrote: post #60
btown wrote: post #54

Earlier quoted context omitted.

There is a valid criticism that when you rely heavily on synthetic outputs, you bring along the precursor model's biases and assumptions without fully knowing the limitations of the data set the precursor model was trained on, as well as intentional adjustments made by the designers of the precursor model to favor certain geopolitical goals. But that's not the criticism that I'm often seeing; it's more that there's a…

Side note about this (great) PG article: its conclusion is that readers are leaving print media to come read online blogs because online content is "more honest" and less formulaic. After 2 years of widespread GPT slop at the top of search engine results, we've definitely come full circle.

Having been an avid net user since the early 90s, I can’t think of a time where that assertion wasn’t specious. In 2005— the year Gmail debuted and people stated using the term “web 2.0”— most of the content on the net was still from traditional media sources— PR garbage and all. Most blogs were still people just rattling off their opinions which was more likely based on the available content than their own high-quality research. And lack of oversight is a double-edged sword: sure you might have been less likely to get pure unfiltered marketing dreck but you were way more likely to get straight-up bullshit, which is a different, but serious problem. I think he was trying to champion the idealistic anti-establishment soul from the early net despite it essentially being an anachronism, even in 2005.

Re: LIMO: Less Is More for Reasoning

#76

Post by sebzim4500 »

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!

I think that "LLMs can never X" is just always false.

Re: LIMO: Less Is More for Reasoning

#77

Post by jkhdigital »

sega_sai wrote: post #34
easeout wrote: post #28

My guess at the upshot: Some domains, like math, are general but have outsized effective vocabularies like all possible numbers, which makes them more expensive to train by the same method that works for domains of regular-sized vocabularies. If you train for reasoning steps in such a problem domain, you can reinforce the comparatively few general terms of the vocabulary like "add", "inverse", "solve". And that leave…

A connected question -- has there been an LLM that is a perfect calculator ? I.e. you give it a expression involving standard operations +/- and (say) integer numbers, standard operations and it should returns always a correct result. I don't remember seeing any papers on this (but i'm not an expert)

Why would you ever want an LLM that is a perfect calculator? Humans invented calculators for a reason. A good LLM should respond to arithmetic questions by executing a cheap and efficient calculator program instead of wasting cycles on it.

Re: LIMO: Less Is More for Reasoning

#78

Post by emorning3 »

bwfan123 wrote: post #57
emorning3 wrote: post #32

My conclusion from all that I'm reading lately is that LLMs cannot do deduction but they can fake it real good. I mean, you wouldn't use this brand of AI to plot your path to Mars. Well, you could, BUT you'll also want to validate the path or risk dying. But this AI is good enough for Elon and his ilk. Because Elon's not gonna get into the capsule, you are. Because you are not the master of this AI, you are the valid…

indeed, these machines do a great mimicry of "reasoning", we get fooled by it. the word reasoning has been subverted by those pushing these llms, and we all have bought-in. quite a magic trick this illusionist has pulled on us.

Yep.

There's gonna come a time when Elon's gonna tell the AI to tell us to push all the buttons, just to see if we'll do it. And I'm pretty sure we will.

Re: LIMO: Less Is More for Reasoning

#79

Post by orbital-decay »

highfrequency wrote: post #33

Cool result, but worth highlighting two points: - Model is finetuned from Qwen-2.5 Instruct, which includes millions of specially filtered math examples in both pretraining and supervised fine-tuning already. - To generate the perfect 817 math examples for LIMO, they used state of the art models like R1 to filter down from an initial pool of 10 million math problems. In other words, a whole lot of intelligence was us…

>In other words, a whole lot of intelligence was used to craft a maximally informative and distilled set of fine-tuning data.

Sounds like any textbook. (and generally the process of knowledge compression over generations that made us who we are)

Re: LIMO: Less Is More for Reasoning

#80

Post by ashirviskas »

whattheheckheck wrote: post #51
gmueckl wrote: post #26

Earlier quoted context omitted.

Calling human knowledge small is hyperbole. I cannot get any LLM even close to giving accurate answers related to the things I know. They simply do not know what I, a single human being, knows. That's simply because I'm a subject matter expert on somewhat niche topics. There are easily hundreds of thousands of people like me out there. There's simply no way an LLM can even train on all of that because each bit of tru…

Where you you instruct others to go to find out more about those niche topics?

Nice try, AI company AI bot /s

Though I'm not even sure about "/s", it is more than feasible to build such a bot that would gather quality information sources.

Post reply on HN