Secure Multifaceted-RAG: Hybrid Knowledge Retrieval with Security Filtering
Information · 16.09.2025 · 16 (9) · 804
DOI: 10.3390/info16090804 ↗Kurz gefasst
Fachartikel in der Zeitschrift Information, online erschienen am 16.09.2025. Verfasst von Grace Byun und 3 weiteren Autor:innen. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
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 79.3–91.9% win rates across correctness, richness, and helpfulness in LLM-based evaluation and 56.3–70.4% in human evaluation. This highlights SecMulti-RAG as a practical and secure solution for enterprise RAG.
Zitieren
APA
Byun, G., Lee, S., Choi, N., & Choi, J. D. (2025). Secure Multifaceted-RAG: Hybrid Knowledge Retrieval with Security Filtering. Information, 16(9), 804. https://doi.org/10.3390/info16090804
Vancouver
Byun G, Lee S, Choi N, Choi JD. Secure Multifaceted-RAG: Hybrid Knowledge Retrieval with Security Filtering. Information. 2025;16(9):804. doi:10.3390/info16090804
BibTeX
@article{Byun2025,
author = {Byun, Grace and Lee, Shinsun and Choi, Nayoung and Choi, Jinho D.},
title = {Secure Multifaceted-RAG: Hybrid Knowledge Retrieval with Security Filtering},
journal = {Information},
year = {2025},
volume = {16},
number = {9},
pages = {804},
doi = {10.3390/info16090804}
}
EUVIMED