I work in a non-profit and continue to use traditional NLP for the same reasons. I have lots of text, and LLMs are expensive. Also, our organization has restrictive policies on AIs, especially LLMs.

I try to get the best of both words by using LLMs to generate synthetic data to train NLP classifiers. First, I use LLMs to generate variations of human-labeled data. Second, I use LLMs to label unlabeled data.

In a future challenge, I want to train LLMs to generate data to train NER for segmenting documents and extracting information.