arXiv：cs.AI· Haoben Huang, Shuxin Liu, Ou Wu, Di Gao·· 5 小时前
重新审视知识编辑中的涟漪效应：JNO 框架如何联合优化邻域
Revisiting Ripple Effects in Knowledge Editing through Pressure-Aware Joint Neighborhood Optimization
AI 导读
研究提出 Joint Neighborhood Optimization（JNO）知识编辑框架，通过 Pressure-Aware Coordination（PAC）和语义预执行门控，在目标规划阶段联合应对可编辑侧协调与保留侧泄漏两种设计压力。在 RippleEdits 上，JNO 将传播与保留指标提升至少 7.0%，并保持跨主干编辑稳定性。
正文
Abstract: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.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2606.01610 [cs.AI] |
| (or arXiv:2606.01610v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2606.01610 arXiv-issued DOI via DataCite |
Submission history
From: Shuxin Liu [view email]
[v1]
Mon, 1 Jun 2026 03:00:13 UTC (9,067 KB)
[v2]
Tue, 13 Oct 2026 12:25:15 UTC (10,102 KB)
来源：arXiv：cs.AI · arxiv.org