解决大模型持续编辑中的性能退化问题，提升长期知识更新能力。
Lifelong Knowledge Editing requires Better Regularization
- 将编辑过程拆解为定位与修正两步，精准定位退化根源。
- 引入早停和范数约束，使模型可支持1万次编辑且提速42%-61%。
- 适合需要长期维护知识的AI系统开发者使用。
知识编辑是提升大语言模型事实准确性的重要方法，但近期研究发现连续编辑会导致模型性能显著下降。本文将流行的定位-编辑方法形式化为两阶段微调过程，精确识别出退化原因：(1) 内部激活过度优化，(2) 编辑矩阵持续范数增长。为此，我们提出两种正则化技术：(1) 最大概率早停（MPES），(2) 显式Frobenius范数约束。实验表明，在编辑关键节点应用这些简单有效的正则化方法，可显著缓解模型退化。结合二者后，定位-编辑方法可扩展至10,000次编辑，同时减少42%-61%的编辑时间。结果表明，针对性正则化对长期知识编辑至关重要。
原文摘要 · Abstract (English)
Knowledge editing is a promising way to improve factuality in large language models, but recent studies have shown significant model degradation during sequential editing. In this paper, we formalize the popular locate-then-edit methods as a two-step fine-tuning process, allowing us to precisely identify the root cause of this degradation. We show that model degradation occurs due to (1) over-optimization of internal activations and (2) continuous norm-growth of edited matrices. To mitigate these issues, we introduce two regularization techniques: (1) Most-Probable Early Stopping (MPES) and (2) explicit Frobenius norm-constraint. We demonstrate that applying these simple yet effective regularization techniques at key points in the editing process can substantially mitigate model degradation. Combining these regularization methods enables scaling locate-then-edit methods to 10,000 edits while reducing editing time by 42-61%. These results show that targeted regularization is essential for lifelong knowledge editing.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。