AI engineering glossary · LLM training alignment
What is self-instruct?
Self-instruct: A method for bootstrapping instruction data: start from a small seed set of human-written tasks, ask a language model to generate new instructions and answers, filter poor or duplicate ones, and use the result to fine-tune. It reduces the need for manual annotation.
Self-instruct: an example
175 seed tasks are expanded to tens of thousands of new instructions written by the model itself.
Related terms
More LLM training alignment terms
- Self-rewarding language models
- Self-Taught Reasoner
- Sequence packing
- Sequence-level distillation
- Simple preference optimisation
- Soft labels
- Span corruption
- Superficial alignment hypothesis
Where you learn it
Self-instruct is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.