Self-consistency (SC) has been a widely used decoding strategy for
chain-of-thought reasoning. Despite bringing significant performance
improvements across a variety of multi-step reasoning tasks, it is a high-cost
method that requires multiple sampling with the preset size. In this paper, we
propose a simple and scalable sampling process, \textbf{E}arly-Stopping
\textbf{S}elf-\textbf{C}onsistency (ESC), to greatly reduce the cost of SC
without sacrificing performance. On this basis, one control scheme for ESC is
further derivated to dynamically choose the performance-cost balance for
different tasks and models. To demonstrate ESC's effectiveness, we conducted
extensive experiments on three popular categories of reasoning tasks:
arithmetic, commonsense and symbolic reasoning over language models with
varying scales. The empirical results show that ESC reduces the average number
of sampling of chain-of-thought reasoning by a significant margin on six
benchmarks, including MATH (-33.8%), GSM8K (-80.1%), StrategyQA (-76.8%),
CommonsenseQA (-78.5%), Coin Flip (-84.2%) and Last Letters (-67.4%), while
attaining comparable performances.

我们提出了一种简单且可扩展的采样过程 ESC，用于减少 Self-consistency 的成本，并在不牺牲性能的情况下动态选择性能成本平衡的控制方案。通过在算术、常识和符号推理任务上进行实验证明，ESC 显著降低了链式思维推理的平均采样数量，同时具有可比性的性能。