Holistic Explainable AI (H-XAI): Extending Transparency Beyond Developers in AI-Driven Decision Making
This work addresses the need for more inclusive and adaptable AI transparency for stakeholders beyond developers, though it appears incremental as it builds on existing XAI and causal methods.
The paper tackles the problem that current explainable AI (XAI) methods primarily serve developers and lack support for diverse stakeholder needs, introducing Holistic-XAI (H-XAI) as a unified framework that integrates causal rating methods with traditional XAI to enable interactive, multi-method explanations, demonstrated through case studies in credit risk classification and financial time-series forecasting.
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.