保护隐私的LLM知识图谱查询生成方法
Ask Safely: Privacy-Aware LLM Query Generation for Knowledge Graphs
- 根据图结构识别敏感信息并隐藏其值
- 在不泄露隐私前提下保持查询准确率
- 适合处理含敏感数据的知识图谱场景
大型语言模型（LLMs）因具备强大的语义理解与推理能力，被广泛用于查询知识图谱（KGs）。然而，当知识图谱包含敏感信息且用户无法本地访问生成模型时，隐私安全成为关键挑战。为此，我们提出一种隐私感知的查询生成方法：基于图结构识别敏感信息，并在向LLM请求将自然语言问题转换为Cypher查询前，主动隐藏这些敏感值。实验表明，该方法能有效防止敏感数据被传输至第三方服务，同时维持较高的查询准确率。
原文摘要 · Abstract (English)
Large Language Models (LLMs) are increasingly used to query knowledge graphs (KGs) due to their strong semantic understanding and extrapolation capabilities compared to traditional approaches. However, when KGs contain sensitive information and users lack local access to generative models, privacy becomes a critical concern. To address this issue, we propose a privacy-aware query generation approach for KGs. Our method identifies sensitive information in the graph based on its structure and omits such values before requesting the LLM to translate natural language questions into Cypher queries. Experimental results show that our approach effectively prevents sensitive data from being transmitted to third-party services, while maintaining a high level of query accuracy.
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。