Large language models (LLMs) with Chain-of-thought (CoT) have recently emerged as a powerful technique for eliciting reasoning to improve various downstream tasks. As most research mainly focuses on English, with few explorations in a multilingual context, the question of how reliable this reasoning capability is in different languages is still open. To address it directly, we study multilingual reasoning consistency across multiple languages, using popular open-source LLMs. First, we compile the first large-scale multilingual math reasoning dataset, mCoT-MATH, covering eleven diverse languages. Then, we introduce multilingual CoT instruction tuning to boost reasoning capability across languages, thereby improving model consistency. While existing LLMs show substantial variation across the languages we consider, and especially low performance for lesser resourced languages, our 7B parameter model mCoT achieves impressive consistency across languages, and superior or comparable performance to close- and open-source models even of much larger sizes.

通过多语言推理一致性研究，我们构建了第一个大规模的多语言数学推理数据集mCoT-MATH，然后引入多语言CoT指令调节以提高模型的推理能力和一致性。我们的7B参数模型mCoT在各种语言上展现出惊人的一致性，并且在性能上优于或与更大规模的闭源和开源模型相媲美。

mCoT: 多语言指导调整以提升语言模型的推理一致性