RAG-PHI: RAG-driven parallel human and parallel intelligence

Abstract

The advancement of large models offers new perspectives and foundation intelligence for building parallel human ecosystems comprised of biological humans, digital humans, and robotic humans. However, challenges such as time-limited updates to knowledge, inadequate specialized capabilities, and risks of information privacy leakage persist in the management and control of complex systems. To tackle these issues, a retrieval-augmented generation-driven parallel human and parallel intelligence framework (RAG-PHI) is introduced. It proposes to establish an open data platform that facilitates the integration of real-time, industry-specific, and private knowledge into the parallel human system. It develops dynamic routing and retrieval for context capture and the reconfiguration of parallel human capabilities, along with introducing context-aware prompt learning to enhance cognitive and behavioral skills. Furthermore, towards the organization and management, training and evaluation, operation and production of parallel human, the structures of parallel human community, parallel human school, and parallel human factory are proposed by the RAG-PHI architecture. These are designed to foster a parallel human ecosystem powered by RAG and large foundation models, thereby enhancing productivity in the age of intelligent industries.

Keywords

• retrieval-augmented generation;parallel human;parallel intelligence;large model