面向企业的安全多面RAG：带安全过滤的混合知识检索
Secure Multifaceted-RAG for Enterprise: Hybrid Knowledge Retrieval with Security Filtering
AI总结：
针对企业RAG检索范围有限和数据安全风险，提出SecMulti-RAG框架，通过混合内部文档、预生成专家知识与外部LLM知识，并结合安全过滤和本地开源生成器，在汽车报告生成任务中显著提升正确性、丰富性和有用性。
摘要：
现有的检索增强生成（RAG）系统在企业环境中面临检索范围有限和数据安全风险的挑战。当相关内部文档不可用时，系统难以生成准确且完整的响应。此外，使用闭源大语言模型（LLMs）引发了泄露专有信息的担忧。为解决这些问题，我们提出了安全多面RAG（SecMulti-RAG）框架，该框架不仅从内部文档中检索，还从两个补充来源检索：针对预期查询预生成的专家知识，以及按需生成的外部LLM知识。为降低安全风险，我们采用本地开源生成器，并且仅在过滤机制判定提示安全时选择性地使用外部LLM。该方法提高了完整性，防止了数据泄露，并降低了成本。我们在汽车行业报告生成任务上的评估中，SecMulti-RAG显著优于传统RAG——在基于LLM的评估中，在正确性、丰富性和有用性方面取得了79.3%至91.9%的胜率，在人工评估中取得了56.3%至70.4%的胜率。这表明SecMulti-RAG是企业RAG的一种实用且安全的解决方案。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
