知识神经元中心之旅：语言无关知识神经元与退化知识神经元的发现
Journey to the Center of the Knowledge Neurons: Discoveries of Language-Independent Knowledge Neurons and Degenerate Knowledge Neurons
AI总结：
本文提出架构自适应多语言集成梯度方法精确定位知识神经元，发现语言无关知识神经元和功能重叠的退化知识神经元，揭示多语言预训练模型事实知识存储机制。
摘要：
预训练语言模型（PLMs）包含大量事实知识，但知识在参数中的存储方式仍不清楚。本文深入探讨了理解多语言PLMs中事实知识存储方式的复杂任务，并引入了架构自适应多语言集成梯度方法，该方法相比现有方法能更精确地定位知识神经元，且在各种架构和语言中更具通用性。此外，我们对知识神经元进行了深入探索，得出以下两个重要发现：（1）发现了语言无关知识神经元，它们以超越语言的形式存储事实知识。我们设计了跨语言知识编辑实验，证明PLMs可以基于语言无关神经元完成此任务；（2）发现了退化知识神经元，这是一种新型神经元，表明不同的知识神经元可以存储相同的事实。其功能重叠的特性赋予PLMs对事实知识的稳健掌握。我们设计了事实核查实验，证明退化知识神经元能帮助PLMs检测错误事实。实验结果证实了这些发现，揭示了多语言PLMs中事实知识存储的机制，并为该领域贡献了宝贵的见解。代码可在https://github.com/heng840/AMIG获取。
英文摘要：
Pre-trained language models (PLMs) contain vast amounts of factual knowledge, but how the knowledge is stored in the parameters remains unclear. This paper delves into the complex task of understanding how factual knowledge is stored in multilingual PLMs, and introduces the Architecture-adapted Multilingual Integrated Gradients method, which successfully localizes knowledge neurons more precisely compared to current methods, and is more universal across various architectures and languages. Moreover, we conduct an in-depth exploration of knowledge neurons, leading to the following two important discoveries: (1) The discovery of Language-Independent Knowledge Neurons, which store factual knowledge in a form that transcends language. We design cross-lingual knowledge editing experiments, demonstrating that the PLMs can accomplish this task based on language-independent neurons; (2) The discovery of Degenerate Knowledge Neurons, a novel type of neuron showing that different knowledge neurons can store the same fact. Its property of functional overlap endows the PLMs with a robust mastery of factual knowledge. We design fact-checking experiments, proving that the degenerate knowledge neurons can help the PLMs to detect wrong facts. Experiments corroborate these findings, shedding light on the mechanisms of factual knowledge storage in multilingual PLMs, and contribute valuable insights to the field. The code is available at https://github.com/heng840/AMIG.
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。
