X-SYS: A Reference Architecture for Interactive Explanation Systems

TL;DR

X-SYS is a comprehensive reference architecture designed to facilitate the development of interactive explanation systems in AI, emphasizing system capabilities, quality attributes, and practical implementation exemplified by SemanticLens.

Contribution

The paper introduces X-SYS, a structured architecture that connects user interfaces with system components, addressing operational challenges in deploying explainability in AI systems.

Findings

X-SYS organizes system design around four key quality attributes.

SemanticLens demonstrates the practical application of X-SYS principles.

The architecture enables independent evolution of interface and backend components.

Abstract

The explainable AI (XAI) research community has proposed numerous technical methods, yet deploying explainability as systems remains challenging: Interactive explanation systems require both suitable algorithms and system capabilities that maintain explanation usability across repeated queries, evolving models and data, and governance constraints. We argue that operationalizing XAI requires treating explainability as an information systems problem where user interaction demands induce specific system requirements. We introduce X-SYS, a reference architecture for interactive explanation systems, that guides (X)AI researchers, developers and practitioners in connecting interactive explanation user interfaces (XUI) with system capabilities. X-SYS organizes around four quality attributes named STAR (scalability, traceability, responsiveness, and adaptability), and specifies a five-component decomposition (XUI Services, Explanation Services, Model Services, Data Services, Orchestration and Governance). It maps interaction patterns to system capabilities to decouple user interface evolution from backend computation. We implement X-SYS through SemanticLens, a system for semantic search and activation steering in vision-language models. SemanticLens demonstrates how contract-based service boundaries enable independent evolution, offline/online separation ensures responsiveness, and persistent state management supports traceability. Together, this work provides a reusable blueprint and concrete instantiation for interactive explanation systems supporting end-to-end design under operational constraints.