Knowledge editing systems must update selected facts while preserving nearby but irrelevant behavior. This paper studies this problem in a memory-assisted setting where an edit memory is retrieved at inference time and a parameter-efficient adapter corrects the model's object preference. We argue that the central design question is not only how to write an edit, but also when to suppress it. We introduce \method{}, a route-specialized dual-adapter editor. A relevance router first decides whether a prompt should receive an edit memory. Routed prompts use an edit adapter trained to prefer the new object over the original object; unrouted non-direct prompts use a separate locality adapter trained to preserve or restore the original-object preference. We evaluate \method{} on three 1,000-case protocols, \cf{}, \zsre{}, and \mquake{}, under the same memory protocol and two 7B/8B base models. On Llama-3.1-8B-Instruct, \method{} obtains the best overall probability-preference accuracy on all three benchmarks: 0.8180 on \cf{}, 0.8946 on \zsre{}, and 0.9922 on \mquake{}. The same trend holds on Qwen3-8B. Router ablations show that the relevant memory boundary differs across datasets: a lexical neural router is safest on \cf{}, while BGE embedding routing is better on \zsre{} and \mquake{}. Component and module ablations show that the gain mainly comes from separating edit injection from off-route suppression rather than from simply increasing LoRA capacity.

翻译：知识编辑系统需更新选定事实的同时保持邻近但不相关行为不变。本文在记忆辅助场景下研究该问题，其中编辑记忆在推理时被检索，参数高效适配器校正模型的目标偏好。我们论证核心设计问题不仅在于如何写入编辑，更在于何时抑制编辑。为此提出\method{}，一种路由专业化的双适配器编辑器。相关性路由器首先判定提示是否应接收编辑记忆：被路由的提示使用训练为偏好新对象而非原始对象的编辑适配器；未被路由的非直接提示使用独立的局部性适配器以保持或恢复原始对象偏好。我们在相同记忆协议下，基于三个含1000个案例的基准协议\cf{}、\zsre{}和\mquake{}以及两个7B/8B基础模型评估\method{}。在Llama-3.1-8B-Instruct上，\method{}在三个基准上均取得最佳整体概率-偏好准确率：\cf{}为0.8180，\zsre{}为0.8946，\mquake{}为0.9922。Qwen3-8B上呈现相同趋势。路由器消融实验表明相关记忆边界因数据集而异：词法神经路由器在\cf{}上最为安全，而BGE嵌入路由在\zsre{}和\mquake{}上表现更优。组件与模块消融实验显示性能提升主要源于分离编辑注入与离路由抑制，而非单纯增加LoRA容量。