Holistic Explainable AI (H-XAI): Extending Transparency Beyond Developers in AI-Driven Decision Making

2025-08-07

AI Summary

Existing XAI methods primarily target developers and focus on post-hoc plausibility verification, failing to address the heterogeneous needs of diverse stakeholders—including regulators, end users, and decision-makers—regarding individual explanations, group-level fairness assessment, and model robustness analysis. To bridge this gap, we propose H-XAI, the first framework that tightly integrates causal scoring with post-hoc explainability techniques, enabling a dynamic explanation paradigm supporting interactive querying, hypothesis testing, and comparative analysis against both random and biased baselines. H-XAI delivers adaptive, multi-objective explanations across granularities (instance-level and global) and dimensions (interpretability, fairness, robustness). We validate its generality and effectiveness across six real-world scenarios in credit risk assessment and financial time-series forecasting.

Technology Category

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

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Fairness, privacy, and diversity in economic environments

Abstract

Current eXplainable AI (XAI) methods largely serve developers, often focusing on justifying model outputs rather than supporting diverse stakeholder needs. A recent shift toward Evaluative AI reframes explanation as a tool for hypothesis testing, but still focuses primarily on operational organizations. We introduce Holistic-XAI (H-XAI), a unified framework that integrates causal rating methods with traditional XAI methods to support explanation as an interactive, multi-method process. H-XAI allows stakeholders to ask a series of questions, test hypotheses, and compare model behavior against automatically constructed random and biased baselines. It combines instance-level and global explanations, adapting to each stakeholder's goals, whether understanding individual decisions, assessing group-level bias, or evaluating robustness under perturbations. We demonstrate the generality of our approach through two case studies spanning six scenarios: binary credit risk classification and financial time-series forecasting. H-XAI fills critical gaps left by existing XAI methods by combining causal ratings and post-hoc explanations to answer stakeholder-specific questions at both the individual decision level and the overall model level.

Problem

• Extends XAI transparency beyond developers to diverse stakeholders
• Integrates causal rating with XAI for interactive hypothesis testing
• Addresses individual and model-level questions using multi-method explanations

Innovation

• Integrates causal rating with traditional XAI
• Supports interactive multi-method explanation process
• Combines instance-level and global explanations