A Simple Architecture for Enterprise Large Language Model Applications based on Role based security and Clearance Levels using Retrieval-Augmented Generation or Mixture of Experts
This addresses security and information access problems for enterprise users, but it appears incremental as it builds on existing RAG and MoE methods.
The study proposes an architecture for enterprise LLM applications that uses role-based security and clearance levels to filter documents in RAG and experts in MoE, aiming to prevent information leakage by addressing current LLMs' limitations in handling security and access.
This study proposes a simple architecture for Enterprise application for Large Language Models (LLMs) for role based security and NATO clearance levels. Our proposal aims to address the limitations of current LLMs in handling security and information access. The proposed architecture could be used while utilizing Retrieval-Augmented Generation (RAG) and fine tuning of Mixture of experts models (MoE). It could be used only with RAG, or only with MoE or with both of them. Using roles and security clearance level of the user, documents in RAG and experts in MoE are filtered. This way information leakage is prevented.