[svc0]

I think it should be noted that this enforces grammatical constraints on the model's generated text, but it doesn't do anything to properly align the content. This would be useful if you needed to ensure a server delivered well-formatted JSON, but it I suspect it wont solve a lot of alignment issues with current language generation. For example current iterations of Llama and GPT often do not label markdown code-blocks correctly. Using grammar-based sampling, you could enforce that it labels code blocks but you couldn't enforce correct labeling since this is context-dependent. You also couldn't invent a novel domain-specific language without aligning against that language and expect good output.

[newhouseb]

Also important to call out that anytime you have a freeform string it's pretty much an open invitation for the LLM to go completely haywire and run off into all sorts of weird tangents. So these methods are best used with other heuristics to bias sampling once you get to free-form text territory (i.e. a repetition penalty etc)

[brucethemoose2]

But since its llama, some examples could be trained into a lora.

I can imagine a system where, for instance, a markdown lora and a markdown grammar file can be hotswapped in and out.