The recent progress in large language models (LLMs), especially the invention
of chain-of-thoughts (CoT) prompting, makes it possible to solve reasoning
problems. However, even the strongest LLMs are still struggling with more
complicated problems that require non-linear thinking and multi-step reasoning.
In this work, we explore whether LLMs have the ability to recognize their own
errors, without resorting to external resources. In particular, we investigate
whether they can be used to identify individual errors within a step-by-step
reasoning. To this end, we propose a zero-shot verification scheme to recognize
such errors. We then use this verification scheme to improve question-answering
performance, by using it to perform weighted voting on different generated
answers. We test the method on three math datasets-GSM8K, MathQA, and MATH-and
find that it successfully recognizes errors and, in turn, increases final
predictive performance.

最近大语言模型（LLM），特别是链式思维（CoT）提示的发明，使得解决推理问题成为可能。本文探讨 LLMs 是否具备识别自身错误的能力，无需外部资源。具体而言，我们研究它们是否能够用于识别逐步推理中的个别错误。为此，我们提出了一种零 - shot 验证方案来识别这些错误。然后，我们使用这个验证方案来提高问题回答的性能，通过对不同生成答案进行加权投票。我们在三个数学数据集 - GSM8K，MathQA 和 MATH 上测试了该方法，发现它成功地识别错误，并进而提高了最终的预测性能。