Self-Consistency Improves Chain of Thought Reasoning in Language Models

TL;DR

This paper introduces a self-consistency decoding method for chain-of-thought prompting in large language models, which samples multiple reasoning paths and selects the most consistent answer, significantly improving reasoning accuracy.

Contribution

It proposes a novel self-consistency decoding strategy that enhances chain-of-thought prompting by leveraging multiple reasoning paths for better accuracy.

Findings

Self-consistency improves performance on arithmetic and commonsense benchmarks.

Significant accuracy gains on GSM8K, SVAMP, AQuA, StrategyQA, and ARC-challenge.

Sampling multiple reasoning paths leads to more reliable answers.

Abstract

Chain-of-thought prompting combined with pre-trained large language models has achieved encouraging results on complex reasoning tasks. In this paper, we propose a new decoding strategy, self-consistency, to replace the naive greedy decoding used in chain-of-thought prompting. It first samples a diverse set of reasoning paths instead of only taking the greedy one, and then selects the most consistent answer by marginalizing out the sampled reasoning paths. Self-consistency leverages the intuition that a complex reasoning problem typically admits multiple different ways of thinking leading to its unique correct answer. Our extensive empirical evaluation shows that self-consistency boosts the performance of chain-of-thought prompting with a striking margin on a range of popular arithmetic and commonsense reasoning benchmarks, including GSM8K (+17.9%), SVAMP (+11.0%), AQuA (+12.2%), StrategyQA (+6.4%) and ARC-challenge (+3.9%).