一致性表象之下：探索大语言模型中的跨语言知识表示共享
Beneath the Surface of Consistency: Exploring Cross-lingual Knowledge Representation Sharing in LLMs
AI总结：
本研究通过知识编辑方法测量大语言模型跨语言事实知识表示共享程度，发现高一致性不等于共享表示，文字相似性是主导因素，完全共享可提升最佳语言准确率平均达150%。
摘要：
事实性陈述的真实性在很大程度上与其所使用的语言无关。然而，语言模型在跨语言回答相同事实性问题的能力上却存在不一致性。这引发了关于大语言模型如何跨语言表示给定事实的问题。我们通过两个方面探索多语言事实性知识：模型跨语言一致回答查询的能力，以及将答案“存储”在多种语言共享表示中的能力。我们提出了一种方法，通过重新利用知识编辑技术来测量跨语言表示共享的程度。我们使用一个新的多语言数据集，考察了具有不同多语言配置的大语言模型。我们发现，高一致性并不一定意味着共享表示，尤其是对于使用不同文字的语言。此外，我们发现文字相似性是表示共享的主导因素。最后，我们观察到，如果大语言模型能够完全跨语言共享知识，那么它们在表现最佳语言上的准确率平均可提升高达150%。这些发现凸显了改进大语言模型中多语言知识表示的必要性，并为开发更稳健、更一致的多语言大语言模型指明了路径。
英文摘要：
The veracity of a factoid is largely independent of the language it is written in. However, language models are inconsistent in their ability to answer the same factual question across languages. This raises questions about how LLMs represent a given fact across languages. We explore multilingual factual knowledge through two aspects: the model's ability to answer a query consistently across languages, and the ability to ''store'' answers in a shared representation for several languages. We propose a methodology to measure the extent of representation sharing across languages by repurposing knowledge editing methods. We examine LLMs with various multilingual configurations using a new multilingual dataset. We reveal that high consistency does not necessarily imply shared representation, particularly for languages with different scripts. Moreover, we find that script similarity is a dominant factor in representation sharing. Finally, we observe that if LLMs could fully share knowledge across languages, their accuracy in their best-performing language could benefit an increase of up to 150\% on average. These findings highlight the need for improved multilingual knowledge representation in LLMs and suggest a path for the development of more robust and consistent multilingual LLMs.
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。
