Secure Multifaceted-RAG for Enterprise: Hybrid Knowledge Retrieval with Security Filtering
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915395938549760 |
|---|---|
| author | Byun, Grace Lee, Shinsun Choi, Nayoung Choi, Jinho D. |
| author_facet | Byun, Grace Lee, Shinsun Choi, Nayoung Choi, Jinho D. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_13425 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Secure Multifaceted-RAG for Enterprise: Hybrid Knowledge Retrieval with Security Filtering Byun, Grace Lee, Shinsun Choi, Nayoung Choi, Jinho D. Computation and Language 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. |
| title | Secure Multifaceted-RAG for Enterprise: Hybrid Knowledge Retrieval with Security Filtering |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2504.13425 |