Large language models are having their Stable Diffusion moment

Re:Large language models are having their Stable Diffusion m... by Der_Einzige on Sunday March 12, 2023 @04:25AM (#35117976)

I feel bad for not being active on Twitter, specifically because I missed out on stuff like this (which predates my paper). I should have cited this thread since it's evidence that someone else had utilized this technique in my paper!

I think this vocabulary filtering technique will pick up steam again now that good quality open source LLMs are proliferating. I've always wanted to try these techniques with ChatGPT, and the inability to do so has caused me to somewhat publicly complain about their lack of access to ChatGPT's vocabulary probability distribution (they don't give more than the top 10 most likely continuations).

[ Parent | on HN ]

Re:Large language models are having their Stable Diffusion m... by kastnerkyle on Monday March 13, 2023 @12:28PM (#35138010)

You might be interested in this thread from 2019 here on HN as well, I linked to a line of work on constrained sequence generation from Sony CSL that is pretty nifty https://news.ycombinator.com/item?id=21334639

As an aside - do you have any academic references for masking / constraining based next step transitions? It's a trick I've been messing with for years, but I probably picked this up from some older poetry generation work. Haven't been able to find any direct reference for simple 1 step masking, let alone more involved things like constraining based on the unrolled, modified markov sequence or things bigger than 1 step.

[ Parent | on HN ]

Re:Large language models are having their Stable Diffusion m... by Der_Einzige on Tuesday March 14, 2023 @01:44AM (#35147838)

I think that this is what you will be looking for

https://huggingface.co/blog/constrained-beam-search

This technique has been quietly available within HF for awhile, and has a lot of real world use-cases.

[ Parent | on HN ]

Re:Large language models are having their Stable Diffusion m... by kastnerkyle on Saturday March 25, 2023 @10:32AM (#35303008)

For any models where you get access to the code (counting HF in this), definitely a lot of tooling available - and this tool looks really nice hadn't seen it before! Hope similar levels of control can become available for the bigger, less accessible systems, even though people don't want to expose token log-likelihoods there should be ways.

I've also been reading your paper on these topics, based on previous comments on HN. So thanks for that! Always interested in work about constrained generation.

I'd really like to see some version of the techniques from this palindrome generation https://www.ijcai.org/Proceedings/15/Papers/353.pdf revisited in modern contexts. Or some of the other Sony CSL work on this topic (e.g. https://www.francoispachet.fr/wp-content/uploads/2021/01/pap...) which I will admit I (still) do not understand yet.

[ Parent | on HN ]