X-SYS: A Reference Architecture for Interactive Explanation Systems
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918442192338944 |
|---|---|
| author | Labarta, Tobias Hoang, Nhi Dreyer, Maximilian Berend, Jim Hein, Oleg Ma, Jackie Samek, Wojciech Lapuschkin, Sebastian |
| author_facet | Labarta, Tobias Hoang, Nhi Dreyer, Maximilian Berend, Jim Hein, Oleg Ma, Jackie Samek, Wojciech Lapuschkin, Sebastian |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_12748 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | X-SYS: A Reference Architecture for Interactive Explanation Systems Labarta, Tobias Hoang, Nhi Dreyer, Maximilian Berend, Jim Hein, Oleg Ma, Jackie Samek, Wojciech Lapuschkin, Sebastian Artificial Intelligence Human-Computer Interaction Software Engineering 68t01 (Primary), 68u35 (Secondary), 68t05 (Secondary) D.2.11; H.5.2; H.3.3; I.2.6 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. |
| title | X-SYS: A Reference Architecture for Interactive Explanation Systems |
| topic | Artificial Intelligence Human-Computer Interaction Software Engineering 68t01 (Primary), 68u35 (Secondary), 68t05 (Secondary) D.2.11; H.5.2; H.3.3; I.2.6 |
| url | https://arxiv.org/abs/2602.12748 |