Composable Building Blocks for Controllable and Transparent Interactive AI Systems

2025-06-02

AI Summary

Interactive AI systems suffer from architectural opacity, poor interpretability, and limited controllability due to model black-box nature. Method: This paper proposes a transparency-oriented architecture based on composable, structured modules—including AI models and control logic—introducing a novel “structure + visualization” dual-track modular design. It integrates both post-hoc and inherently interpretable XAI techniques, defines an LLM-coordinated explanation protocol, and implements a visual explanation interface with explicit dataflow and API specifications. Contribution/Results: The work establishes the first end-to-end interactive modeling framework enabling human-AI co-understanding. A prototype system empirically validates consistent behavioral understanding across developers, end users, and LLMs, significantly improving system controllability and debugging efficiency.

Technology Category

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

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Search and Retrieval-Augmented AI: Assisted, interactive, and conversational search

Abstract

While the increased integration of AI technologies into interactive systems enables them to solve an equally 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. To this end, we propose an approach to represent interactive systems as sequences of structural building blocks, such as AI models and control mechanisms grounded in the literature. These can then be explained through accompanying visual building blocks, such as XAI techniques. The flow and APIs of the structural building blocks form an explicit overview of the system. This serves as a communication basis for both humans and automated agents like LLMs, aligning human and machine interpretability of AI models. We discuss a selection of building blocks and concretize our flow-based approach in an architecture and accompanying prototype interactive system.

Problem

• Addressing AI black box opacity in interactive systems
• Enhancing transparency via composable structural building blocks
• Aligning human and machine interpretability of AI models

Innovation

• Structural building blocks for interactive AI systems
• Visual building blocks for XAI techniques
• Flow-based approach for transparent system architecture