Speaker unverified: evaluation

Transcript context

…Being in distribution at least keeps you within the bounds of what it was trained for. So I will offer a personal experience here. I spend a lot of time doing example, few-shot prompting and tweaking for my AI newsletter, which goes out every single day. And I see a lot of failures. I don't really have a good playground to improve them. Actually, I wonder if you have a good few-shot example playground tool to recommend. You have six things. Example of quality, ordering, distribution, quantity, format, and similarity. I will say quantity. I guess quality is an example. I have the unique problem, and maybe you can help me with this, of my exemplars leaking into the output, which I actually don't want. I didn't see an example of a mitigation step of this in your report, but I think this is tightly related to quantity. So quantity, if you only give one example, it might repeat that back to you. So if you give two examples, like I used to always have this rule of every example must come in pairs. A good example, bad example, good example, bad example. And I did that. Then it just started repeating back my examples to me in the output. So I'll just let you riff. What do you do when people run into this? First of all, in-distribution is definitely a better term than what I used before, so thank you for that. And you're right, we don't cover that problem in the problem report. I actually didn't really know about that problem until afterwards when I put out a tweet. I was saying, what are your commonly used formats for few-shot prompting? And one of the responses was a format that included instructions that said, do not repeat any of the examples I gave you. And I guess that is a straightforward solution that might some... No, it doesn't work. Oh, it doesn't work. That is tough. I guess I haven't really had this problem. It's just probably a matter of the tasks I've been working on. So one thing about showing good examples, bad examples, there are a number of papers which have found that the label of the exemplar doesn't really matter, and the model reads the exemplars and cares more about structure than label. You could say we have like a... We're doing few-shot prompting for binary classification. Super simple problem, it's just like, I like pears, positive. I hate people, negative. And then one of the exemplars is incorrect. I started saying exemplars, by the way, which is rather unfortunate. So let's say one of our exemplars is incorrect, and we say like, I like apples, negative, and like colon negative. Well, that won't affect the performance of the model all that much, because the main thing it takes away from the few-shot prompt is the structure of the output rather than the content of the output. That being said, it will reduce performance to some extent, us making that mistake, or me making that mistake. And I still do think that the content is important, it's just apparently not as important as the structure. Got it. Yeah, makes sense. I actually might tweak my approach based on that, because I was trying to give bad examples of do not do this, and it still does it, and maybe that doesn't work. So anyway, I wanted to give one offering as well, which is some sites. So for some of my prompts, I went from few-shot back to zero-shot, and I just provided generic templates, like fill in the blanks, and then kind of curly braces, like the thing you want, that's it. No other exemplars, just a template, and that actually works a lot better. So few-shot is not necessarily better than zero-shot, which is counterintuitive, because you're working harder.…

Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.