多语言语言模型中的跨语言编辑
Cross-lingual Editing in Multilingual Language Models
AI总结：
本文提出跨语言模型编辑（XME）范式，研究多语言模型中单语言事实编辑对其他语言的传播，实验发现现有编辑技术在跨书写体系语言上性能受限，并公开了数据集和代码。
摘要：
大型语言模型（LLMs）的训练需要大量的数据和计算资源，而更新过时的LLMs则需要大量的精力和资源。尽管已经出现了许多模型编辑技术（METs）来高效地更新模型输出而无需重新训练，但它们在多语言LLMs中的有效性（其中知识以多种语言存储）仍是一个研究不足的领域。本研究论文引入了跨语言模型编辑（XME）范式，即在一种语言中编辑一个事实，并观察后续更新在其他语言中的传播。为了研究XME范式，我们使用BLOOM、mBERT和XLM-RoBERTa进行了实验，使用了两种书写体系：拉丁语（英语、法语和西班牙语）和印度语（印地语、古吉拉特语和孟加拉语）。结果揭示了最先进的METs在XME设置下的显著性能限制，特别是当涉及的语言属于两个不同的书写体系家族时。这些发现强调了对XME技术进行进一步研究和开发以解决这些挑战的必要性。有关更全面的信息，本研究中使用的数据集和相关代码可在以下URL公开获取：https://github.com/lingo-iitgn/XME。
英文摘要：
The training of large language models (LLMs) necessitates substantial data and computational resources, and updating outdated LLMs entails significant efforts and resources. While numerous model editing techniques (METs) have emerged to efficiently update model outputs without retraining, their effectiveness in multilingual LLMs, where knowledge is stored in diverse languages, remains an underexplored research area. This research paper introduces the cross-lingual model editing (\textbf{XME}) paradigm, wherein a fact is edited in one language, and the subsequent update propagation is observed across other languages. To investigate the XME paradigm, we conducted experiments using BLOOM, mBERT, and XLM-RoBERTa using the two writing scripts: \textit{Latin} (English, French, and Spanish) and \textit{Indic} (Hindi, Gujarati, and Bengali). The results reveal notable performance limitations of state-of-the-art METs under the XME setting, mainly when the languages involved belong to two distinct script families. These findings highlight the need for further research and development of XME techniques to address these challenges. For more comprehensive information, the dataset used in this research and the associated code are publicly available at the following URL\url{https://github.com/lingo-iitgn/XME}.
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。
