About This Document
- sl:arxiv_author :
- sl:arxiv_firstAuthor : Eric Zelikman
- sl:arxiv_num : 2203.14465
- sl:arxiv_published : 2022-03-28T03:12:15Z
- sl:arxiv_summary : 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.@en
- sl:arxiv_title : STaR: Bootstrapping Reasoning With Reasoning@en
- sl:arxiv_updated : 2022-05-20T13:52:54Z
- sl:bookmarkOf : https://arxiv.org/abs/2203.14465
- sl:creationDate : 2023-02-07
- sl:creationTime : 2023-02-07T16:40:38Z
Documents with similar tags (experimental)