解决大模型知识编辑中的元素重叠问题，提升准确性
SetKE: Knowledge Editing for Knowledge Elements Overlap
- 同时编辑多个共享元素的知识三元组，避免冲突
- 在包含重叠元素的场景下，性能优于现有方法
- 适合需要高精度知识更新的场景，如医疗、法律
大语言模型在检索和问答任务中表现优异，但需更新以融入新知识并减少错误与幻觉。传统方法如微调和增量学习存在过拟合和计算成本高的问题。知识编辑（KE）虽具潜力，却常忽视知识元素重叠（KEO）现象——多个三元组共享相同元素，导致编辑冲突。我们发现现有KE数据集中普遍存在KEO，并证实其对当前方法造成显著性能下降。为此，提出知识集编辑（KSE）新范式，引入SetKE方法，可同步编辑一组三元组。实验表明，SetKE在主流LLM上对KEO场景的处理效果优于现有方法。此外，构建了含KEO三元组的EditSet数据集，提供全面基准。
原文摘要 · Abstract (English)
Large Language Models (LLMs) excel in tasks such as retrieval and question answering but require updates to incorporate new knowledge and reduce inaccuracies and hallucinations. Traditional updating methods, like fine-tuning and incremental learning, face challenges such as overfitting and high computational costs. Knowledge Editing (KE) provides a promising alternative but often overlooks the Knowledge Element Overlap (KEO) phenomenon, where multiple triplets share common elements, leading to editing conflicts. We identify the prevalence of KEO in existing KE datasets and show its significant impact on current KE methods, causing performance degradation in handling such triplets. To address this, we propose a new formulation, Knowledge Set Editing (KSE), and introduce SetKE, a method that edits sets of triplets simultaneously. Experimental results demonstrate that SetKE outperforms existing methods in KEO scenarios on mainstream LLMs. Additionally, we introduce EditSet, a dataset containing KEO triplets, providing a comprehensive benchmark.
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。