Self-Taught Reasoner
Also called STaR.
The Self-Taught Reasoner (STaR) bootstraps reasoning ability by having a model generate rationales, keeping those that lead to correct answers, and fine-tuning on them in repeated rounds.
Description
For problems it fails, STaR provides the correct answer as a hint and asks the model to produce a rationale for it, a step called rationalization.
Sources
- Zelikman et al. (2022). STaR: Bootstrapping Reasoning With Reasoning.
Cite this entry
Protologue. (2026). Self-Taught Reasoner. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.0.0, PTL-0086). https://protologue.com/t/self-taught-reasoner/
BibTeX
@misc{protologue_self_taught_reasoner,
title = {Self-Taught Reasoner},
author = {{Protologue}},
year = {2026},
howpublished = {Protologue: A Taxonomy of Prompting and LLM Techniques, v1.0.0},
note = {Entry PTL-0086},
url = {https://protologue.com/t/self-taught-reasoner/}
}