“STaR: Bootstrapping Reasoning With Reasoning”, Eric Zelikman, Yuhuai Wu, Noah D. Goodman2022-03-28 (, , ; backlinks; similar)⁠:

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 [self-distillation]: 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 substantially improves performance on multiple datasets compared to a model fine-tuned to directly predict final answers, and performs comparably to fine-tuning a 30× larger state-of-the-art language model on CommensenseQA.

Thus, STaR lets a model improve itself by learning from its own generated reasoning.