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

Can LLMs learn from a single example?

fast.ai

Post reply on HN
Print view View original

91–100 of 143 posts

Re: Can LLMs learn from a single example?

#91

Post by d4rkp4ttern »

theonlybutlet wrote: post #89
famouswaffles wrote: post #3

Earlier quoted context omitted.

In the palm-e paper ( https://palm-e.github.io/ ), when they try to unfreeze and train the LLM on new image data only, there is expectedly a lot of CF on NLP tasks but very interestingly, the effect diminishes greatly with the scale of the LLM prior to training. From an average -87.3% performance drop on the 12B model to -61.6% on the 84B model then just -3.9% on the 562B model. Felt like we were just shy of an insig…

What does CF stand for?

Catastrophic Forgetting

Re: Can LLMs learn from a single example?

#92

Post by Angostura »

jph00 wrote: post #2

Thank you for posting this to HN! :D I'm one of the authors of this post -- Johno & I found it really interesting looking into this curious issue of rapid memorization from LLMs. I've been working with neural nets for 30 years, and fine-tuning language models since 2017, and this behavior is most surprising to me! Other folks have seen it in LLMs too, although I haven't seen a analysis of this kind before (although w…

As a lay-person, can I just say I appreciated the accessible writing style. Thanks!

Re: Can LLMs learn from a single example?

#93

Post by PaulHoule »

I’ve observed the same phenomenon with fine-tuning LLMs and I thought it was pretty strange but so far as I could tell other people were observing the same thing but mostly not commenting on it. The conclusion I’d draw is that you’re not going to benefit greatly from adding more data when your model behaves like this.

Overconfidence bugs moe because if you want to turn predictions into decisions and actions you have to be calibrated. I’ve found that some of these models that look like they are over fitting on loss are actually still improving on AUc (matters to me more than accuracy) and I can put a calibrator after the model to get the results I want.

(Still, for my current problem which has noisy labels, I find embedding + classical ML performs as well and takes a fraction of the time as fine tuning and clearly shows benefit trained on more examples than FT does. If I was going to do more model engineering on this problem I would probably resort to “stacking”)

Re: Can LLMs learn from a single example?

#94

Post by Nevermark »

jph00 wrote: post #78
Nevermark wrote: post #70

Do people really use the phrase “over confident” in this way? It is very misleading. What is happening is called “over fitting”. Think of data as dots. A model that generalizes well will create as simple of a function as possible that fits the training data points pretty well. But keep training and parameters will often get very large, creating huge up and down swings in the function curve, far outside the actual dat…

No I don't use the term overfitting for a model where the accuracy is getting better. I think it's misleading.

Over fitting literally means what it says, fitting the training data too well to maintain a well formed function.

This is many decades old terminology for a well established effect that occurs for all curve fitting, function approximation, parameter optimizing, and model training algorithms.

You can Google it with no other context: “over fitting”. [0]

“Confidence” isn’t its name and its meaning has nothing to do with the effect.

Nothing wrong with making up terminology for new effects, but this one is an oldie.

[0] https://www.google.com/search?q=over+fitting&ie=UTF-8&oe=UTF...

Re: Can LLMs learn from a single example?

#95

Post by TeMPOraL »

vvrm wrote: post #57
jph00 wrote: post #4

Earlier quoted context omitted.

I think our experiments actually don't show catastrophic forgetting! The accuracy does not decrease as loss gets worse -- it's simply getting over-confident. So I'm not even sure we're showing any problem to solve here -- it might be more of a opportunity, in fact!

I have been training a natural intelligence model for 3 years now and she still doesn’t get nuance. Things are either good or bad in her book: nothing in between. My plan is to let her train with binary good/bad labels till the age of 5 and then start smoothing the labels after that. Wonder if that works for your AI.

Related trick: I found that training two Natural Intelligence (NI) models in parallel, and having them train each other for most of the time, leads to significant leaps in capabilities. Notably, when one NI picks up a skill, it often results in spontaneous transfer learning - the other NI picks that skill up very quickly, much faster than it would through direct training.

This scales well, too. There are facilities that provide services of co-hosting and cross-training up to ~two dozen NI models in a shared environment - in my experience, this provides similar training benefits to running multiple NIs on your own, at fraction of the cost.

(The facilities are exploiting some neat economies of scale. Talking to some employees, I learned that the transfer learning and co-activation are embarrassingly scalable: if you get two-three NIs to pick up a thing, all the rest immediately follow.)

Re: Can LLMs learn from a single example?

#97

Post by calrain »

Probably unrelated, but I tried to get ChatGPT to write me some code to programmatically control the details of a column filter in an Excel spreadsheet in PowerShell.

Nothing it tried worked, it got close, but it didn't work.

Finally I found some C# code that fixed the problem, and I pasted that code into ChatGPT, asked it to read it, and then fix the problem in PowerShell.

It said it understood the solution, updated the script, and it worked perfectly.

For some reason that behavior was pretty eye opening. Providing material in the question that it wasn't trained on made it solve it.

It's understandable how it did it from language training, it just felt very cool that LLM's can do that.

Re: Can LLMs learn from a single example?

#98

Post by mjburgess »

DougBTX wrote: post #83
mjburgess wrote: post #80

Earlier quoted context omitted.

Accuracy is very rarely a useful metric. It's more an engineering metric than something a user would ever care about. What users want is to have their own credences properly calibrated by engaging with some system. From a physics textbook, they want a systematic presentation of ideas which allows them to build intuitions etc. It's important to formulate the actual goal of the system, rather than just the engineer's g…

This is mixing two meanings of confidence which could lead to confusion. The OP is using confidence to describe how high the per-token probability scores are, while you are talking about the confidence expressed in the tone of voice of the language generated by the model. Really those are orthogonal issues. (Eg, a model could predict with high probability that a output should be “I don’t know”)

It seems like i'm mixing them, but i'm not.

I'm saying as a matter of fact ChatGPT should have different confidences in propositions. My issue isnt the tone of voice, my issue is the content of what it's saying is wrong wrt what we care about, ie., expert credences (/confidences) in the claims it's generating.

It can "express confidently" scepticism; it does not. That's the issue.

In my lang above i was mostly using credence to talk about the strength of the mental state of belief; and confidence to talk about the model of that used in statistical AI.

Re: Can LLMs learn from a single example?

#99

Post by Filligree »

rafaelero wrote: post #13

That's intriguing. But what I want to see is if that one example can change the whole web of knowledge previously established. So, for example, if we finetune the model with a sentence like "Scientists discovered that a type of antigen can make a host immune to HIV" will it then be able to infer that "mRNA vaccines are a valid preventive approach to AIDS since they may be able to express a type of resistance known to…

That would be impressive and surprising. Humans aren’t capable of that.
Post reply on HN