解决大模型编辑中知识遗漏和干扰问题，提升准确性与稳定性。
Resolving UnderEdit & OverEdit with Iterative & Neighbor-Assisted Model Editing
- 通过多次迭代编辑缓解知识注入不足问题。
- 引入邻近知识辅助，减少对无关知识的干扰。
- 适用于各类编辑方法，提升多模型、多任务表现。
大型语言模型广泛应用于下游任务，但通过重新训练或微调来更新其知识往往计算成本高昂。模型编辑通过仅更新目标参数子集提供更高效替代方案，通常遵循定位-编辑范式。尽管效率高，现有方法仍存在局限：编辑可能无法成功注入知识（知识遗漏），或意外破坏相关邻近知识（知识干扰）。为此，我们提出两种互补方法：迭代模型编辑，通过连续多次编辑缓解知识遗漏；邻近知识辅助编辑，在编辑过程中引入邻近知识以减少知识干扰。大量实验表明，这些技术在多种大模型、算法和基准上均提升了编辑性能，知识遗漏降低最高达38个百分点，知识干扰减少最多6个单位，且可广泛适配任意定位-编辑方法。代码已开源：https://github.com/bhimanbaghel/ResolveUnderOverEdit。
原文摘要 · Abstract (English)
Large Language Models (LLMs) are widely deployed in downstream tasks, but keeping their knowledge up-to-date via retraining or fine-tuning is often computationally expensive. Model editing provides a more efficient alternative by updating a targeted subset of parameters, which often follows the locate-and-edit paradigm. Despite this efficiency, existing methods are limited: edits may fail to inject knowledge (UnderEdit) or unintentionally disrupt unrelated neighboring knowledge (OverEdit). To address these challenges, we propose two complementary methods: iterative model editing, which applies successive edits to mitigate UnderEdit, and neighbor-assisted model editing, which incorporates neighboring knowledge during editing to reduce OverEdit. Our extensive experiments show that these techniques improve editing performance across multiple LLMs, algorithms, and benchmarks, reducing UnderEdit by up to 38 percentage points and OverEdit by up to 6, while remaining broadly applicable to any locate-and-edit method. We release our code at https://github.com/bhimanbaghel/ResolveUnderOverEdit.
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。