Bridging the significant gap between large language model's English and
non-English performance presents a great challenge. While some previous studies
attempt to mitigate this gap with translated training data, the recently
proposed question alignment approach leverages the model's English expertise to
improve multilingual performance with minimum usage of expensive, error-prone
translation. In this paper, we explore how broadly this method can be applied
by examining its effects in reasoning with executable code and reasoning with
common sense. We also explore how to apply this approach efficiently to
extremely large language models using proxy-tuning. Experiment results on
multilingual reasoning benchmarks mGSM, mSVAMP and xCSQA demonstrate that the
question alignment approach can be used to boost multilingual performance
across diverse reasoning scenarios, model families, and sizes. For instance,
when applied to the LLaMA2 models, our method brings an average accuracy
improvements of 12.2% on mGSM even with the 70B model. To understand the
mechanism of its success, we analyze representation space, chain-of-thought and
translation data scales, which reveals how question translation training
strengthens language alignment within LLMs and shapes their working patterns.

在这篇论文中，我们研究了如何利用问题对齐方法提高大型语言模型在非英语性能上的应用，通过对可执行代码推理和常识推理的影响进行探索，并通过代理调整的方式实现对极大型语言模型的高效应用。多语言推理基准测试结果显示，问题对齐方法能够在不同推理场景、模型系列和大小上提升多语言性能。与 LLaMA2 模型相比，我们的方法平均提高了 mGSM 的准确率 12.2%，即使在 70B 模型上也是如此。通过分析表示空间、思维链和翻译数据规模，我们还揭示了问题翻译训练如何增强 LLMs 内部的语言对齐，并塑造它们的工作模式。