Sequential Monte Carlo Steering of Large Language Models using Probabilistic Programs · HackerPapers discussions

Sequential Monte Carlo Steering of Large Language Models using Probabilistic Programs — mentioned by Der_Einzige

Tue, 31 Oct 2023 23:16:18 GMT

Too much money being thrown around on BS in the LLM space, hardly any of it is going to places where it matters. Ignorance on the part of investors. For example, the researchers working hard on better text sampling techniques (i.e. https://arxiv.org/abs/2202.00666), or on better constraint techniques (i.e. like this https://arxiv.org/abs/2306.03081), or on actual negative prompting/CFG in LLMs (i.e. like this https://github.com/huggingface/transformers/issues/24536) are doing far FAR more to advance the state of AI than dozens of VC backed LLM companies operating today. They are all laboring…

Paper and discussion history. A mention is not an endorsement.

Sequential Monte Carlo Steering of Large Language Models using Probabilistic Programs — mentioned by Der_Einzige

Fri, 21 Jul 2023 22:41:24 GMT

I am in love with this, I tried my hand at building a Constrained Text Generation Studio (https://github.com/Hellisotherpeople/Constrained-Text-Genera...), and got published at COLING 2022 for my paper on it (https://paperswithcode.com/paper/most-language-models-can-be...), but I always knew that something like this or the related idea enumerated in this paper: https://arxiv.org/abs/2306.03081 was the way to go. I will have to think about how I can build grammars that force things like syllable counts or syntactic rules. Current LLMs do very poorly on those kinds of tasks due to the…

Paper and discussion history. A mention is not an endorsement.