Large language models (LLMs) require continual updates to rectify outdated or erroneous knowledge. Model editing has emerged as a compelling paradigm for introducing targeted modifications without the computational burden of full retraining. Existing approaches are mainly based on a locate-then-edit framework. However, in sequential editing contexts, where multiple updates are applied over time, they exhibit significant limitations and suffer from catastrophic interference, i.e., new edits compromise previously integrated updates and degrade preserved knowledge. To address these challenges, we introduce EvoEdit, a novel editing strategy that mitigates catastrophic interference through sequential null-space alignment, enabling stable and efficient model editing. By performing sequential null-space alignment for each incoming edit, EvoEdit preserves both original and previously modified knowledge representations and maintains output invariance on preserved knowledge even across long edit sequences, effectively mitigating interference. Evaluations on real-world sequential knowledge-editing benchmarks show that EvoEdit achieves better or comparable performance than prior state-of-the-art locate-then-edit techniques, with up to 3.53 times speedup. Overall, these results underscore the necessity of developing more principled approaches for designing LLMs in dynamically evolving information settings, while providing a simple yet effective solution with strong theoretical guarantees.

翻译：大型语言模型（LLM）需要持续更新以修正过时或错误的知识。模型编辑已成为一种引人注目的范式，它能在无需完全重新训练的计算负担下引入定向修改。现有方法主要基于“定位-编辑”框架。然而，在顺序编辑场景中（即随时间应用多次更新），这些方法表现出显著局限性，并遭受灾难性干扰——新的编辑会破坏先前整合的更新，并损害已保留的知识。为解决这些挑战，我们提出EvoEdit，一种新颖的编辑策略，通过顺序零空间对齐减轻灾难性干扰，实现稳定且高效的模型编辑。通过为每次传入的编辑执行顺序零空间对齐，EvoEdit既能保留原始与先前修改过的知识表征，又能在长编辑序列中维持受保留知识的输出不变性，有效抑制干扰。在真实世界的顺序知识编辑基准测试上的评估表明，EvoEdit相比先前最先进的定位-编辑技术，取得了更优或相当的性能，并实现了高达3.53倍的加速。总体而言，这些结果强调了在动态演变的信息环境中为设计LLM开发更具原则性方法的必要性，同时提供了一个简单高效且具有强理论保证的解决方案。