MATCH: Engineering Transparent and Controllable Conversational XAI Systems through Composable Building Blocks

2025-11-27

AI Summary

Interactive AI systems suffer from opacity due to model black-boxness and tight architectural coupling, rendering holistic transparency unattainable; existing XAI methods enhance only individual model interpretability, failing to support human-AI collaborative understanding and control. Method: We propose a novel paradigm that decouples system architecture from XAI techniques, designing composable, process- and API-driven structural building blocks integrated with explanation modules (e.g., LIME, SHAP) to form MATCH—a dual-track framework combining structured modeling and explainability enhancement. Contribution/Results: MATCH pioneers the elevation of XAI from the model level to the system architecture level, enabling end-to-end traceability, intervention, and collaboration for embedded AI behaviors. Experiments demonstrate significant improvements in system-level understandability and human-AI collaboration efficiency, while supporting flexible integration into existing interactive systems.

Technology Category

• Humans and AI: Explainable AI (XAI) for Human Understanding
• Machine Learning: Transparent, Interpretable, Explainable ML
• Computer Vision: Interpretability, Explainability, and Transparency

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

While the increased integration of AI technologies into interactive systems enables them to solve an increasing number of tasks, the black-box problem of AI models continues to spread throughout the interactive system as a whole. Explainable AI (XAI) techniques can make AI models more accessible by employing post-hoc methods or transitioning to inherently interpretable models. While this makes individual AI models clearer, the overarching system architecture remains opaque. This challenge not only pertains to standard XAI techniques but also to human examination and conversational XAI approaches that need access to model internals to interpret them correctly and completely. To this end, we propose conceptually representing such interactive systems as sequences of structural building blocks. These include the AI models themselves, as well as control mechanisms grounded in literature. The structural building blocks can then be explained through complementary explanatory building blocks, such as established XAI techniques like LIME and SHAP. The flow and APIs of the structural building blocks form an unambiguous overview of the underlying system, serving as a communication basis for both human and automated agents, thus aligning human and machine interpretability of the embedded AI models. In this paper, we present our flow-based approach and a selection of building blocks as MATCH: a framework for engineering Multi-Agent Transparent and Controllable Human-centered systems. This research contributes to the field of (conversational) XAI by facilitating the integration of interpretability into existing interactive systems.

Problem

• Addresses the black-box problem in AI-integrated interactive systems
• Proposes a framework for transparent and controllable conversational XAI systems
• Enhances interpretability through composable building blocks and established XAI techniques

Innovation

• Composable building blocks for system transparency
• Flow-based framework integrating XAI techniques
• Multi-agent architecture aligning human-machine interpretability