Toward Responsible AI in the Era of Generative AI: A Reference Architecture for Designing Foundation Model-Based Systems

Abstract

To address AI architecture design challenges, we present an architecture evolution of AI systems in the era of foundation models, transitioning from "foundation-model-as-a-connector"to "foundation-model-as-a-monolithic architecture."We then identify key design decisions and propose a pattern-oriented reference architecture for designing responsible foundation-model-based systems.