mCoT: 面向语言模型推理一致性的多语言指令微调
mCoT: Multilingual Instruction Tuning for Reasoning Consistency in Language Models
AI总结：
针对大语言模型多语言推理可靠性存疑的问题，构建覆盖11种语言的mCoT-MATH数据集，提出多语言CoT指令微调，7B参数的mCoT模型实现跨语言推理一致性和优异性能。
摘要：
具备思维链（Chain-of-thought, CoT）的大语言模型（Large language models, LLMs）近期已成为一种激发推理能力以改进各类下游任务的强大技术。由于多数研究主要聚焦英语，在多语言语境下的探索较少，因此这种推理能力在不同语言中的可靠性如何仍是一个未解决的问题。为直接解决该问题，我们利用主流开源LLMs，研究了跨多语言的多语言推理一致性。首先，我们构建了首个大规模多语言数学推理数据集mCoT-MATH，覆盖11种不同语言。随后，我们提出多语言CoT指令微调方法，以提升跨语言推理能力，进而改善模型一致性。现有LLMs在我们研究的语言间表现差异显著，尤其是低资源语言表现不佳，而我们的7B参数模型mCoT在跨语言上实现了出色的一致性，其性能甚至优于或可比肩规模大得多的闭源与开源模型。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
