STaR: Bootstrapping Reasoning With Reasoning

Eric Zelikman, Yuhuai Wu, Jesse Mu, Noah Goodman

Keywords: chain-of-thought, reasoning, language model, bootstrapping

TL;DR: STaR allows a language model's "chain-of-thought" rationale generation ability to be bootstrapped from a few initial few-shot rationales on datasets without rationales.

Abstract: Generating step-by-step "chain-of-thought" rationales improves language model performance on complex reasoning tasks like mathematics or commonsense question-answering. However, inducing language model rationale generation currently requires either constructing massive rationale datasets or sacrificing accuracy by using only few-shot inference. We propose a technique to iteratively leverage a small number of rationale examples and a large dataset without rationales, to bootstrap the ability to perform successively more complex reasoning. This technique, the "Self-Taught Reasoner" (STaR), relies on a simple loop: generate rationales to answer many questions, prompted with a few rationale examples; if the generated answers are wrong, try again to generate a rationale given the correct answer; fine-tune on all the rationales that ultimately yielded correct answers; repeat. We show that STaR significantly improves performance on multiple datasets compared to a model fine-tuned to directly predict final answers, and performs comparably to fine-tuning a 30$\times$ larger state-of-the-art language model on CommensenseQA. Thus, STaR lets a model improve itself by learning from its own generated reasoning.

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/star-bootstrapping-reasoning-with-reasoning/code)