企业级安全RAG框架，融合多源知识与过滤机制提升准确性和保密性。
Secure Multifaceted-RAG for Enterprise: Hybrid Knowledge Retrieval with Security Filtering
- 融合内部文档、预生成专家知识和按需外部生成知识，扩展检索范围。
- 在汽车报告生成任务中，模型评估胜率79.3%~91.9%，人工评估56.3%~70.4%。
- 本地开源生成+安全过滤，防止数据泄露，适合对隐私要求高的企业场景。
现有检索增强生成（RAG）系统在企业环境中面临检索范围有限和数据安全风险问题。当内部文档不足时，系统难以生成准确完整的内容；使用闭源大模型又存在敏感信息泄露隐患。为此，我们提出安全多维度RAG（SecMulti-RAG）框架，不仅从内部文档检索，还引入两类补充来源：针对预期查询的预生成专家知识，以及按需由外部LLM生成的知识。为降低安全风险，采用本地开源生成器，并通过过滤机制仅在提示被认为安全时启用外部LLM。该方法显著提升内容完整性，防止数据外泄，同时降低成本。在汽车行业报告生成任务中，SecMulti-RAG在基于LLM的评估中取得79.3%至91.9%的胜率，在人工评估中达56.3%至70.4%，展现出良好的实用性和安全性。
原文摘要 · Abstract (English)
Existing Retrieval-Augmented Generation (RAG) systems face challenges in enterprise settings due to limited retrieval scope and data security risks. When relevant internal documents are unavailable, the system struggles to generate accurate and complete responses. Additionally, using closed-source Large Language Models (LLMs) raises concerns about exposing proprietary information. To address these issues, we propose the Secure Multifaceted-RAG (SecMulti-RAG) framework, which retrieves not only from internal documents but also from two supplementary sources: pre-generated expert knowledge for anticipated queries and on-demand external LLM-generated knowledge. To mitigate security risks, we adopt a local open-source generator and selectively utilize external LLMs only when prompts are deemed safe by a filtering mechanism. This approach enhances completeness, prevents data leakage, and reduces costs. In our evaluation on a report generation task in the automotive industry, SecMulti-RAG significantly outperforms traditional RAG - achieving 79.3 to 91.9 percent win rates across correctness, richness, and helpfulness in LLM-based evaluation, and 56.3 to 70.4 percent in human evaluation. This highlights SecMulti-RAG as a practical and secure solution for enterprise RAG.
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。