[HN Gopher] LIMO: Less Is More for Reasoning
___________________________________________________________________
LIMO: Less Is More for Reasoning
Author : trott
Score : 185 points
Date : 2025-02-09 16:33 UTC (6 hours ago)
(HTM) web link (arxiv.org)
(TXT) w3m dump (arxiv.org)
| delichon wrote:
| To see a World in a Grain of Sand And a Heaven in a Wild
| Flower, Hold Infinity in the palm of your hand And
| Eternity in an hour.
| CamperBob2 wrote:
| Come in under the shadow of this impure rock And I
| will show you something different from either Your
| shadow at morning striding behind you Or your shadow at
| evening rising to meet you; I will show you wisdom in a
| handful of sand.
| throwaway314155 wrote:
| what's the connection here? just the words "less is more"?
| doug_durham wrote:
| In the same way that image diffusion models showed that
| convincing approximations of the entire visual world could be
| summarized in a 5GB model, are "reasoning patterns" similarly
| compressible? Are there actually countably few reasoning patterns
| that are used across all domains, and as such can be captured
| with relatively small training sets?
| HarHarVeryFunny wrote:
| I would say there are only a smallish number of truly generic
| "reasoning patterns" (strategies/approaches), but applied
| reasoning not only requires a reasoning "pattern", but also a
| repertoire of valid domain-specific reasoning steps that can be
| applied pursuant to that approach, as well as the combination
| of capabilities it takes to overcome impasses when you've
| exhausted your knowledge and learnt reasoning steps and still
| not got to a solution.
|
| Perhaps in a domain like math a smallish number of math-
| specific reasoning steps will go a long way, but math itself
| also has many "sub-domains" (algebra, geometry, calculus,
| topology, etc) and AFAIK the techniques of one branch are only
| going to be useful in another to extent you can map the problem
| from one domain to another.
| ysofunny wrote:
| where's chatbotAI-zero? in the way alpha-go-zero was the best
| after training with itself? (and only with itself)
| sebastiennight wrote:
| 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?
| CamperBob2 wrote:
| _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?_
|
| https://i.imgur.com/CBmMSqO.png, perhaps
| gpm wrote:
| 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.
| Yoric wrote:
| I think that there is a strong limit to that: if you don't
| understand the proofs, you're going to have a hard time
| understanding when the model explains to you why your code
| is not correct.
| gpm wrote:
| In most cases I expect saying "<this> assertion fires
| with <this> input" is enough to be useful. Or "I can't
| prove <this> assertion doesn't fire, but I don't have a
| counter example either". Assertion used broadly to
| include things like rules for avoiding undefined
| behavior.
|
| Better explanations would be nice of course, but not
| obviously practical. I wouldn't actually trust the AIs
| reasoning much in the first place, only that it can't
| trick the proof checking tool.
| sebastiennight wrote:
| 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.
| gpm wrote:
| 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.
| wongarsu wrote:
| The advantage of alpha-go-zero is that it is constrained to the
| language of go. If you made two LLM train only off each other
| they would develop their own language. Maybe they'd be great at
| reasoning, but we wouldn't understand them. Even humans in that
| situation would develop jargon, and as time goes on a dialect
| or language of their own. And humans are a lot more grounded in
| their language than LLMs.
| jebarker wrote:
| Someone first needs to design a rule set for a game that only
| permits the correct use of language but encompasses the entire
| breadth of language use. Then it's plausible.
|
| Thankfully for mathematics and code this seems plausible due to
| automated theorem proving.
| Chio wrote:
| 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 converse with, not an AI
| for the purpose of other AI.
|
| That said, it seems like a promising area of research:
|
| > DeepSeek-R1-Zero demonstrates capabilities such as self-
| verification, reflection, and generating long CoTs, marking a
| significant milestone for the research community.
|
| [1] https://github.com/deepseek-ai/DeepSeek-R1
| HarHarVeryFunny wrote:
| 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, but hard to come by. One of the main contributions
| of the DeepSeek-R1 paper was describing their "bootstrapping"
| (my term) process whereby they started with a non-reasoning
| model, DeepSeek-V3, and used a three step process to generate
| more and more reasoning data from that (+ a few other
| sources) until they had enough to train DeepSeek-R1, which
| they then further improved with RL.
|
| DeepSeek-R1 Zero isn't a self-play version of DeepSeek-R1 -
| it was just the result of the first (0th) step of this
| bootstrapping process whereby they used RL to finetune
| DeepSeek-V3 into the (somewhat of an idiot savant - one trick
| pony) R1 Zero model that was then capable of generating
| training data for the next bootstrapping step.
| antirez wrote:
| 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, ...
| HarHarVeryFunny wrote:
| 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.
| igleria wrote:
| 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!
| euthydemus wrote:
| https://x.com/mbalunovic/status/1887962694659060204
| bilater wrote:
| I think the way to swallow this bitter pill is to acknowledge
| they can "generalize" because all human knowledge is actually a
| relatively "small" finite distribution that models are now big
| enough to pattern match on.
| gmueckl wrote:
| 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 true expert knowledge necessarily
| comically underrepresented in any possible training set.
| whattheheckheck wrote:
| Where you you instruct others to go to find out more about
| those niche topics?
| ak_111 wrote:
| 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.
| sebzim4500 wrote:
| I think that "LLMs can never X" is just always false.
| hexomancer wrote:
| 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 type of reasoning
| text (think of generative image models a few years ago, where
| appending "unreal engine" to a prompt would significantly improve
| the quality of the output, the reason was that the model was
| trained to generate the distribution of the images on the
| internet, most of them are not particularly impressive, however,
| since images containing "unreal engine" were usually high-quality
| screenshots of images, it would also move the distribution of
| generated images towards higher quality generations). So I think
| the model already has most of the ability, it just needs to
| adjust a few connections to actually utilize this latent skill,
| so it makes sense that a few training examples are enough to
| adjust the connections to increase mathematical reasoning skills.
| cube2222 wrote:
| 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
| zozbot234 wrote:
| 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.
| 827a wrote:
| 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.
| cubefox wrote:
| This suggests fine-tuning a base model (with SL or RL)
| generally doesn't make the model inherently smarter, only the
| initial self-supervised learning during pretraining does.
| Though it would be strange if no amount of reinforcement
| learning could make the LLM truly smarter.
| larodi wrote:
| 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.
| sega_sai wrote:
| It is interesting how the field is becoming 'pedagogy of LLMs'.
| nicr_22 wrote:
| "My Fair Llama" or "Pygmallm"
| Philpax wrote:
| There's already a two-year-old LLM named Pygmalion; it may be
| time to revive that
| https://huggingface.co/PygmalionAI/pygmalion-6b
| ei625 wrote:
| People here should read, especially 1.How to make less datasets
| 2. Categorize reasoning process into L1-L5 when evaluation.
| ei625 wrote:
| For 1, they apply non-reasoning model then apply reasoning
| model.
| easeout wrote:
| 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 leaves the arithmetic of number
| combinations separate from particular problems because you're not
| emphasizing one-shot answers. You can train N reasoning cases + M
| arithmetic cases instead of N*M whole math problems. So you have
| to use more inference power but you can get better answers for
| less training.
|
| Theory aside, I would think a good application-side method is to
| use this general reasoning process to structure a final
| expression and then pass that through a traditional evaluator.
| Then the reasoning and training thereof need only go as far as
| symbol manipulation. This is something like Wolfram Alpha, if its
| NLP handed off to the evaluator much later in the process.
| sega_sai wrote:
| 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)
| Scene_Cast2 wrote:
| Standard neural nets (created through regular training
| methods) have no guarantees about their output. So no, there
| hasn't been anything like that.
|
| I do recall someone handcrafting the weights for a
| transformer and getting some sort of useful algorithm or
| computation going, so there's that.
| antirez wrote:
| the S1 paper did the same a few days ago, basically. 1000 total
| CoT with SFT.
|
| I believe that all this shows that pre-training stage already
| creates the representations needed for CoT reasoning, so they are
| very simple to uncover. Either with R1-Zero pure RL, or with few-
| shots SFT.
| fallmonkey wrote:
| While there're interesting findings here,
| https://arxiv.org/pdf/2502.03373 (also with a lot of good
| findings) suggested some contradicting theory on the critical
| mass of training process/data for the sake of reasoning
| capability.
| emorning3 wrote:
| 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 validator.
| bwfan123 wrote:
| 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.
| highfrequency wrote:
| 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 used to craft a maximally informative and
| distilled set of fine-tuning data. It's not very clear to me if
| this is more or less impressive than getting the same result by
| simply fine-tuning on the 10 million initial pool, but I suppose
| that would make for a worse headline.
| smallerize wrote:
| 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.
| rfoo wrote:
| 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
| pama wrote:
| A big part of why R1 is much slowerr than o3-mini is that
| inference optimization is not yet performed on most
| solutions for serving R1 models (so R1 is rather comparable
| to o1 or o1 pro in terms of latency rather than o1-mini or
| o3-mini). The MoE is already relatively efficient if
| perfectly load balanced in an inference setting and should
| have latencies and throughputs that are equal to or faster
| than equivalent dense models with 37B parameters. In
| practice due to MLA inference should be much faster yet for
| long contexts compared to typical dense models. If DeepSeek
| or someone else tried to distill the model onto another MoE
| architecture with even less active parameters and properly
| implement speculative decoding on top, one could gain
| additional speedups in inference. I imagine we will see
| these things but it takes a bit of time till they are all
| public.
| smallerize wrote:
| I actually forgot that o3-mini was available now. I was
| using o1 numbers.
| rvnx wrote:
| 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.
| amingilani wrote:
| 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.
| carschno wrote:
| 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.
| EGreg wrote:
| 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/2
| 0...
| btown wrote:
| 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 an "unfair" amount of press coverage towards new
| models that rely, in the critics' views, more on distillation
| than on "true" innovation.
|
| It's worth noting that there are many parties with
| significant motivation to build public sympathy that only
| "true" innovation should be valued, and it is only their
| highly-valued investments that can uniquely execute in that
| space. Cutting-edge models built in caves with a box of
| _their_ scraps are counter to that narrative. It 's worth
| considering https://paulgraham.com/submarine.html in this
| context, and understanding whether it is truly "everyone"
| that is critical in this way.
| sebastiennight wrote:
| 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.
| chefandy wrote:
| 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.
| armcat wrote:
| Yes, the authors explicitly highlighted those two points in the
| abstract, in terms of them being the elicitation threshold for
| complex reasoning, namely, an extremely complete pre-trained
| foundation model, and a set of extremely high quality examples
| post-training.
|
| To your question on finetuning on the initial 10 million pool -
| intuitively, it would require tremendous amount of finetuning
| data to move the needle - you really won't be able to move the
| gradients much with just 817 examples, that initial pool is
| effectively enforcing pretty rigid regularization.
|
| There is now an increasing interest in showing that small data
| with inference time scaling is providing significant yield.
| Couple of recent examples:
|
| * TinyZero: https://github.com/Jiayi-Pan/TinyZero * s1 Simple
| Test Time Scaling: https://arxiv.org/abs/2501.19393
| trott wrote:
| Another way to look at this is that there are 12,290 bits of
| information in choosing 817 samples from 10,000,000.
| TOMDM wrote:
| 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.
| shashanoid wrote:
| Love prepending 'explain' to arxiv links these days xD
| https://explainarxiv.org/abs/2502.03387
| pinoy420 wrote:
| I don't have enough karma to downvote adverts.
|
| https://news.ycombinator.com/item?id=42896559
| shashanoid wrote:
| hn broke
| Limoynada wrote:
| If the LIMO hypothesis about the existence of a latent capacity
| for efficient reasoning in small models that can be elicited by
| finetuning the model with a small datasets is true, then we could
| see a huge transference of power from huge models to small models
| and that in a recurrent way seems to offer unlimited power. But
| to feed that loop there should be a property of those datasets,
| they teach the model to adapt reasoning to model size and that is
| verified by the model extending the depth of the reasoning chain
| using a small branching factor in the exploration space, like a
| minimum cover to detect deep patterns.
| xendo wrote:
| Any idea if the same dataset can be used to improve human
| reasoning? Let's say I manually analyze 817 math examples, would
| that be optimal strategy for me to improve my math reasoning? Can
| the same distilation process be applied to leetcode?
| viraptor wrote:
| This training is less about learning how to reason and more
| about conditioning the llm to use self-evaluations
| automatically. You could probably reproduce this effect
| yourself by sticking a paper reminder in front of you and
| writing "after every small step, spend 2 minutes considering if
| it's right and does it work in the context of the task so far;
| evaluate alternatives" on it. (which yes, could improve
| reasoning likely)
| ak_111 wrote:
| It's actually difficult to work out the affiliation of the
| authors for non-Chinese. SJTU = Shanghai Jiao Tong University,
| but couldn't work out GAIR and IIS.
| fpgaminer wrote:
| 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.
| akomtu wrote:
| 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.
___________________________________________________________________
(page generated 2025-02-09 23:00 UTC)