Despite their exceptional capabilities, large language models (LLMs) are prone to generating unintended text due to false or outdated knowledge. Given the resource-intensive nature of retraining LLMs, there has been a notable increase in the development of knowledge editing. However, current approaches and evaluations rarely explore the perturbation of editing on neighboring knowledge. This paper studies whether updating new knowledge to LLMs perturbs the neighboring knowledge encapsulated within them. Specifically, we seek to figure out whether appending a new answer into an answer list to a factual question leads to catastrophic forgetting of original correct answers in this list, as well as unintentional inclusion of incorrect answers. A metric of additivity is introduced and a benchmark dubbed as Perturbation Evaluation of Appending Knowledge (PEAK) is constructed to evaluate the degree of perturbation to neighboring knowledge when appending new knowledge. Besides, a plug-and-play framework termed Appending via Preservation and Prevention (APP) is proposed to mitigate the neighboring perturbation by maintaining the integrity of the answer list. Experiments demonstrate the effectiveness of APP coupling with four editing methods on four LLMs. The code and data are available at https://github.com/mjy1111/PEAK.

翻译：尽管大型语言模型（LLMs）具备卓越能力，但由于知识错误或过时，它们容易生成非预期的文本。鉴于重新训练LLMs的资源密集型特性，知识编辑技术的发展日益受到关注。然而，当前方法及评估方案很少探究编辑操作对邻近知识的扰动影响。本文研究向LLMs更新新知识是否会扰动其内部封装的邻近知识。具体而言，我们试图探究向事实性问题的答案列表追加新答案，是否会导致该列表中原始正确答案的灾难性遗忘，以及是否意外引入错误答案。本文引入了可加性度量指标，并构建了名为“知识追加的扰动评估”（PEAK）的基准测试，以评估追加新知识时对邻近知识的扰动程度。此外，我们提出了一种即插即用框架——通过保持与预防的追加（APP），通过维护答案列表的完整性来减轻邻近扰动。实验表明，APP与四种编辑方法在四种LLMs上的结合具有显著效果。代码与数据公开于https://github.com/mjy1111/PEAK。