Non paywalled

https://arxiv.org/abs/2407.07723

Is it a compression when you need presumably gigabites of a model to reconstruct the data?

It's basically the same as saying I can shatter compressions records by hashing the thing and using a rainbow table to decompress it.

I'd be more interested in lossy compression tho. Few % of image quality loss for multiplying compression ratio is mega useful.

They're using domain-specific LLMs to compress narrow-domain data. Their text compression LLM was trained on, and then tested on, legal text and medical text.

There's no reason one couldn't apply the domain-specific-compressor idea to a conventional lossless text compressor, essentially moving much of the dictionary from the compressed file to the program itself. I don't know if anyone's tried that. I'd like to know how that compares.