多语言知识编辑与语言无关事实神经元
Multilingual Knowledge Editing with Language-Agnostic Factual Neurons
AI总结：
针对多语言知识编辑中的知识冲突问题，本文发现跨语言共享的语言无关事实神经元，并提出LU-LAFNs方法定位更新这些神经元，在Bi-ZsRE和MzsRE基准上取得最佳编辑性能。
摘要：
多语言知识编辑（MKE）旨在同时更新大型语言模型（LLMs）中跨多种语言的事实知识。以往研究表明，LLMs中不同语言的相同知识具有一定程度的可共享性。然而，现有大多数MKE方法忽视了不同语言间相同知识之间的联系，导致知识冲突和编辑性能受限。为解决这一问题，我们首先探究了LLMs如何处理多语言事实知识，发现不同语言中的相同事实知识通常会激活一组共享的神经元，我们称之为语言无关事实神经元（LAFNs）。这些神经元代表了跨语言共享的相同事实知识，并暗示了多语言知识之间的语义联系。受此发现启发，我们提出了一种新的MKE方法，通过定位和更新语言无关事实神经元（LU-LAFNs）来同时编辑多语言知识，从而避免知识冲突并提升编辑性能。在Bi-ZsRE和MzsRE基准上的实验结果表明，我们的方法取得了最佳的编辑性能，证明了建模多语言知识间语义联系的有效性和重要性。
英文摘要：
Multilingual knowledge editing (MKE) aims to simultaneously update factual knowledge across multiple languages within large language models (LLMs). Previous research indicates that the same knowledge across different languages within LLMs exhibits a degree of shareability. However, most existing MKE methods overlook the connections of the same knowledge between different languages, resulting in knowledge conflicts and limited edit performance. To address this issue, we first investigate how LLMs process multilingual factual knowledge and discover that the same factual knowledge in different languages generally activates a shared set of neurons, which we call language-agnostic factual neurons (LAFNs). These neurons represent the same factual knowledge shared across languages and imply the semantic connections among multilingual knowledge. Inspired by this finding, we propose a new MKE method by Locating and Updating Language-Agnostic Factual Neurons (LU-LAFNs) to edit multilingual knowledge simultaneously, which avoids knowledge conflicts and thus improves edit performance. Experimental results on Bi-ZsRE and MzsRE benchmarks demonstrate that our method achieves the best edit performance, indicating the effectiveness and importance of modeling the semantic connections among multilingual knowledge.
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。
