AI engineering glossary · LLM training alignment
What is Self-Taught Reasoner?
Self-Taught Reasoner (also called STaR): A bootstrapping method in which a model writes step-by-step rationales for problems, keeps the rationales that lead to correct answers, and is fine-tuned on them; for failed problems it is shown the correct answer and asked to rationalise. Repeating this improves reasoning without human-written explanations.
Self-Taught Reasoner: an example
A model solves 60 percent of arithmetic word problems, is fine-tuned on its own correct rationales, and then solves more in the next round.
Related terms
More LLM training alignment terms
- Sequence packing
- Sequence-level distillation
- Simple preference optimisation
- Soft labels
- Span corruption
- Superficial alignment hypothesis
- Supervised fine-tuning
- Sycophancy
Where you learn it
Self-Taught Reasoner is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.