Recently, Large Language Models (LLMs) have shown impressive language capabilities. While most of the existing LLMs have very unbalanced performance across different languages, multilingual alignment based on translation parallel data is an effective method to enhance the LLMs' multilingual capabilities. In this work, we discover and comprehensively investigate the spontaneous multilingual alignment improvement of LLMs. We find that LLMs instruction-tuned on the question translation data (i.e. without annotated answers) are able to encourage the alignment between English and a wide range of languages, even including those unseen during instruction-tuning. Additionally, we utilize different settings and mechanistic interpretability methods to analyze the LLM's performance in the multilingual scenario comprehensively. Our work suggests that LLMs have enormous potential for improving multilingual alignment efficiently with great language and task generalization.

翻译：近年来，大语言模型（LLMs）展现出令人瞩目的语言能力。尽管现有大多数LLM在不同语言间的性能存在显著不平衡，基于翻译平行数据的多语言对齐是增强LLM多语言能力的有效方法。本研究发现并系统探究了LLM的自发多语言对齐改进现象。我们发现，在问题翻译数据（即不含标注答案）上进行指令微调的LLM能够促进英语与广泛语言（甚至包括指令微调期间未见过的语言）之间的对齐。此外，我们通过不同设置和机制可解释性方法，全面分析了LLM在多语言场景下的表现。我们的研究表明，LLM在高效提升多语言对齐方面具有巨大潜力，并展现出优异的语言与任务泛化能力。