解决多跳问答中知识编辑的不一致问题，提升模型可靠性。
Consistency-Aware Parameter-Preserving Knowledge Editing Framework for Multi-Hop Question Answering
- 基于知识图谱构建一致性编辑框架，确保更新与推理对齐。
- 在MQuAKE上实现准确率提升，验证方法有效性。
- 适合需要持续更新知识且保持逻辑连贯的问答系统。
参数保持型知识编辑（PPKE）可在不重训练或调整参数的情况下更新模型知识。现有PPKE方法利用知识图谱（KG）将知识编辑能力扩展至多跳问答（MHQA），但常因缺乏一致性导致知识污染、更新不稳定及检索行为偏离预期，削弱了PPKE在多跳推理中的可靠性。本文提出CAPE-KG：一种面向MHQA的具有一致性感知的参数保持型编辑框架。CAPE-KG确保知识图谱的构建、更新与检索始终与MHQA任务需求一致，维持未编辑与已编辑知识间的连贯推理。在MQuAKE基准上的大量实验表明，该方法显著提升了PPKE在多跳问答中的性能，证明了在PPKE中解决一致性问题的有效性。
原文摘要 · Abstract (English)
Parameter-Preserving Knowledge Editing (PPKE) enables updating models with new information without retraining or parameter adjustment. Recent PPKE approaches used knowledge graphs (KG) to extend knowledge editing (KE) capabilities to multi-hop question answering (MHQA). However, these methods often lack consistency, leading to knowledge contamination, unstable updates, and retrieval behaviors that are misaligned with the intended edits. Such inconsistencies undermine the reliability of PPKE in multi-hop reasoning. We present CAPE-KG, Consistency-Aware Parameter-Preserving Editing with Knowledge Graphs, a novel consistency-aware framework for PPKE on MHQA. CAPE-KG ensures KG construction, update, and retrieval are always aligned with the requirements of the MHQA task, maintaining coherent reasoning over both unedited and edited knowledge. Extensive experiments on the MQuAKE benchmark show accuracy improvements in PPKE performance for MHQA, demonstrating the effectiveness of addressing consistency in PPKE.
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。