Linguistically-informed LLMs Perform Better // Chris Brousseau // LLMs in Prod Conference

// Abstract
It’s silly to think of training and using large LANGUAGE models without any sort of input from the study of language itself. Linguistics is not the only field of knowledge that improve LLMs, as they are the intersection of several fields, however, they can help us not only improve current model performance but also clearly see where future improvements will come.

// Bio
If you need generative AI for Star Wars stuff, hire me right now. If you …

abstract chris conference fields intersection knowledge language language models large language large language models linguistics llms prod study think training