IXAII: An Interactive Explainable Artificial Intelligence Interface for Decision Support Systems

2025-06-26

AI Summary

Existing explainable AI (XAI) methods are predominantly static, overlooking user diversity and interactive requirements, thereby limiting explanatory effectiveness. To address this, we propose IXAII—the first integrated XAI system framework that unifies multiple explanation techniques, role-aware adaptation, and real-time interactivity. IXAII incorporates four state-of-the-art local and counterfactual explanation methods—LIME, SHAP, Anchors, and DiCE—and supports on-demand customization of explanation content and visualization formats for five distinct user roles. Through synergistic design of user modeling, multi-view visualizations, and an interactive frontend, IXAII bridges the gap among algorithmic interpretability, human cognitive constraints, and practical deployment needs. Empirical evaluations with domain experts and non-expert users demonstrate that IXAII’s multi-explanation orchestration and format controllability significantly enhance decision transparency, model trustworthiness, and depth of user understanding.

Technology Category

• Humans and AI: Explainable AI (XAI) for Human Understanding
• Machine Learning: Transparent, Interpretable, Explainable ML
• Philosophy and Ethics of AI: Accountability, Interpretability & Explainability

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
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Although several post-hoc methods for explainable AI have been developed, most are static and neglect the user perspective, limiting their effectiveness for the target audience. In response, we developed the interactive explainable intelligent system called IXAII that offers explanations from four explainable AI methods: LIME, SHAP, Anchors, and DiCE. Our prototype provides tailored views for five user groups and gives users agency over the explanations' content and their format. We evaluated IXAII through interviews with experts and lay users. Our results indicate that IXAII, which provides different explanations with multiple visualization options, is perceived as helpful to increase transparency. By bridging the gaps between explainable AI methods, interactivity, and practical implementation, we provide a novel perspective on AI explanation practices and human-AI interaction.

Problem

• Develops interactive explainable AI for decision support
• Addresses static methods lacking user perspective
• Provides tailored explanations for diverse user groups

Innovation

• Interactive explainable AI system IXAII
• Combines LIME, SHAP, Anchors, DiCE methods
• Tailored views for diverse user groups