Constrained-Text-Generation-Studio

I wrote the relevant paper about this: https://arxiv.org/abs/2306.15926 https://github.com/Hellisotherpeople/Constrained-Text-Genera...

I have proof from my commit history on the readme to CTGS[1] that my usage of the term "Photoshop for Creative Writing" (What I tried to market it as) predates all of this by... years now. https://github.com/Hellisotherpeople/Constrained-Text-Genera... I'm obsessed with this idea of a proper LLM desktop class prosumer front-end. Something feeling like it was made by Adobe in a world where they didn't go to shit in the early 2010s. Blender, but for LLMs. Oobabooga, but actually good and not janky. It would ideally implement all forms of "representation engineering" and hacking or playing with the embedding/latent spaces, along with every other LLM feature folks would love to have but often don't know exist (i.e. constrained generation) If you're a VC type reading this and believe in this idea, I really want to talk to you right about now.

Oh my god. I wrote a whole library called "Constrained Text Generation Studio" where I mused that I wanted a "Photoshop for Text". I'm not even sure which work predates the other: https://github.com/Hellisotherpeople/Constrained-Text-Genera... The core idea of a "photoshop for text", specifically a word processor made for prosumers supporting GenAI first class (i.e oobabooga but actually good) - is worth so much. If you're a VC reading this, chances are I want to talk to you to actually execute on the idea from the OP

I was working on this stuff before it was cool, so in the sense of the precursor to LLMs (and sometimes supporting LLMs still) I've built many things: 1. Games you can play with word2vec or related models (could be drop in replaced with sentence transformer). It's crazy that this is 5 years old now: https://github.com/Hellisotherpeople/Language-games 2. "Constrained Text Generation Studio" - A research project I wrote when I was trying to solve LLM's inability to follow syntactic, phonetic, or semantic constraints: https://github.com/Hellisotherpeople/Constrained-Text-Genera... 3. DebateKG - A bunch of "Semantic Knowledge Graphs" built on my pet debate evidence dataset (LLM backed embeddings indexes synchronized with a graphDB and a sqlDB via txtai). Can create compelling policy debate cases https://github.com/Hellisotherpeople/DebateKG 4

I'll shamelessly plug my somewhat related but even less polished take on a text generation studio. I was fascinated by the idea of constraining an LLMs vocabulary and it ended up as a publication and this: https://github.com/Hellisotherpeople/Constrained-Text-Genera...

My mental model for LLMs was built by carefully studying the distribution of its output vocabulary at every time step. There are tools that allow you to right click and see all possible continuations for an LLM like you would in a code IDE[1]. Seeing what this vocabulary is[2] and how trivial modifications to the prompt can impact probabilities will do a lot for improving the mental model of how LLM operate. Shameless self plug, but software which can do what I am describing is here, and it's worth noting that it ended up as peer reviewed research. [1] https://github.com/Hellisotherpeople/Constrained-Text-Genera... [2] https://github.com/Hellisotherpeople/Constrained-Text-Genera...

Yeah, the LLM outputs a distribution of likely next tokens. It is up to the decoder to select one, and it can use a grammar to enforce certain rules on the output. https://github.com/Hellisotherpeople/Constrained-Text-Genera... or https://github.com/ggerganov/llama.cpp/blob/master/grammars/... for example.

Sad to see that my related work on token-level constrained text generation is not cited in the paper: https://github.com/Hellisotherpeople/Constrained-Text-Genera... https://aclanthology.org/2022.cai-1.2/

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 tokenization schemes...

It's far too easy to destroy any type of RLHF done to try to prevent bad behavior from an LLM, and just "fixing the dataset" doesn't really help. For example, if you want a LLM to generate things that look like social security numbers, you may try to prompt it asking for social security numbers. It will of course give you "I'm sorry hal I can't do that..." Then start using a technique like token filtering/filter assisted decoding, to make it where the LLM can only generate hyphens and numbers, and suddenly it does what you ask despite RLHF I explored this a tiny bit in the later sections of my paper studying what happens when you restrict an LLMs vocabulary: https://aclanthology.org/2022.cai-1.pdf#page=17 You can even play with this with open source models using CTGS: https://github.com/Hellisotherpeople/Constrained-Text-Genera... Now we

I agree with you, and I'm SHOCKED at how little work there actually is in phonetics within the NLP community. Consider that most of the phonetic tools that I am using to enforce rhyming or similar syntactic constrained in constrained text generation studio (https://github.com/Hellisotherpeople/Constrained-Text-Genera...) were built circa 2014, such as the CMU rhyming dictionary. In most cases, I could not find better modern implementations of these tools. I did learn an awful lot about phonetic representations and matching algorithms. Things like "soundex" and "double metaphone" now make sense to me and are fascinating to read about.

Yup! I wrote a whole paper and constrained text generation studio about this which has gotten some positive attention: https://github.com/Hellisotherpeople/Constrained-Text-Genera... https://replicate.com/blog/turn-your-llm-into-a-poet

Re: constraints, it turns out that banning tokens in a vocabulary is a great way to force models to be creative and follow syntactic or semantic constraints without errors: https://github.com/hellisotherpeople/constrained-text-genera...

Lol all of this is stuff that is trivially fixed with constrained text generation studio: https://github.com/hellisotherpeople/constrained-text-genera... Just ban the damn tokens and try again. I wish that folks had more intuition around tokenization, and why LLMs struggle to follow syntactic, lexical, or phonetic constraints.