让大模型编辑知识时保持逻辑一致，自动更新相关事实。
ChainEdit: Propagating Ripple Effects in LLM Knowledge Editing through Logical Rule-Guided Chains
- 用知识图谱规则引导大模型推理，生成逻辑连贯的知识链。
- 相比基线，逻辑泛化能力提升超30%，且编辑精准可靠。
- 适合需要高逻辑一致性知识更新的场景，如医疗、法律领域。
当前大语言模型的知识编辑方法在传播涟漪效应至相关事实时难以保持逻辑一致性。我们提出ChainEdit框架，通过融合知识图谱导出的逻辑规则与大模型的内在推理能力，实现系统性链式更新。该方法自动从结构化知识库中提取逻辑模式，并与大模型内部逻辑对齐，动态生成并编辑逻辑关联的知识簇。实验表明，在逻辑泛化能力上相比基线提升超过30%，同时保持编辑的可靠性与特异性。我们进一步通过知识感知评估协议，消除现有基准中的评价偏差，有效解耦外部依赖。本工作在涟漪效应传播任务上达到新SOTA，确保知识编辑后的内部逻辑一致性。
原文摘要 · Abstract (English)
Current knowledge editing methods for large language models (LLMs) struggle to maintain logical consistency when propagating ripple effects to associated facts. We propose ChainEdit, a framework that synergizes knowledge graph-derived logical rules with LLM logical reasoning capabilities to enable systematic chain updates. By automatically extracting logical patterns from structured knowledge bases and aligning them with LLMs' internal logics, ChainEdit dynamically generates and edits logically connected knowledge clusters. Experiments demonstrate an improvement of more than 30% in logical generalization over baselines while preserving editing reliability and specificity. We further address evaluation biases in existing benchmarks through knowledge-aware protocols that disentangle external dependencies. This work establishes new state-of-the-art performance on ripple effect while ensuring internal logical consistency after knowledge editing.
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。