新方法同时优化知识编辑的传播与保留，避免副作用。
Revisiting Ripple Effects in Knowledge Editing through Pressure-Aware Joint Neighborhood Optimization
- 联合优化目标区域表示，兼顾可编辑性和稳定性
- 在RippleEdits数据集上提升传播与保留指标至少7.0%
- 适合需要精准可控知识更新的研究者
大语言模型中的单次知识编辑可能引发局部知识邻域的涟漪效应：理想情况下的相关事实扩散与被保留事实的意外扰动。现有方法分别处理这两种效应，未显式建模其耦合关系。本文通过分析典型基线的涟漪响应，识别出两种耦合设计压力：可编辑端协调与被保留端泄漏。提出联合邻域优化（JNO）框架，在目标规划阶段统一建模并解决这两类压力。JNO通过压力感知协调（PAC）机制，在耦合约束下联合优化邻域目标表示，并引入语义预执行门控机制，在参数更新前拒绝高风险目标方案。在RippleEdits基准上的实验表明，JNO在传播和保留指标上均提升至少7.0%，同时保持跨骨干模型的编辑稳定性。
原文摘要 · Abstract (English)
Single-edit updates in large language models can trigger ripple effects across local knowledge neighborhoods: desirable propagation to related facts and unintended perturbation of preserved ones. Existing methods address these two effects separately, without explicitly modeling their coupling. We challenge this separation through an analysis of ripple responses across typical baselines, identifying two coupled design pressures: editable-side coordination and preserved-side leakage. We propose Joint Neighborhood Optimization (JNO), a new knowledge-editing framework to formalize and jointly address both pressures at the target-planning stage. JNO instantiates this principle through Pressure-Aware Coordination (PAC), which jointly optimizes neighborhood target representations under coupled constraints, and a semantic pre-execution gate that rejects high-risk target plans before parameter execution. Experiments on RippleEdits show JNO improves propagation and preservation metrics by at least 7.0% while preserving cross-backbone editing stability.
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。