AI engineering glossary · LLM training alignment
What is DAPT (domain-adaptive pretraining)?
Domain-adaptive pretraining (also called DAPT): Continuing unsupervised training on text from one specific field, such as medicine, finance or law, so the model absorbs its vocabulary and facts before it is fine-tuned on a labelled task in that field.
Domain-adaptive pretraining: an example
A base model is further pretrained on clinical notes and then fine-tuned to extract diagnoses.
Related terms
More LLM training alignment terms
Where you learn it
Domain-adaptive pretraining is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.