Meta-Explainers: A Unified Ensemble Approach for Multifaceted XAI

Abstract

Artifcial intelligence (AI) systems are increasingly adopted in high-stakes domains such as healthcare and fnance, so the demand for transparency and interpretability has grown substantially. EXplainable AI (XAI) methods have emerged to address this challenge, but individual techniques often ofer limited, fragmented insights. Tis paper introduces Meta-explainers, a novel ensemble-based XAI framework that integrates multiple explanation types—specifcally relevance-based and counterfactual methods—into unifed, multifaceted and complementary meta-explanations. Inspired by meta-classifcation principles, our approach structures the explanation process into fve stages: generation, grouping, evaluation, aggregation, and visualization. Each stage is designed to preserve the unique strengths of individual XAI techniques while enhancing their interpretability and coherence when combined. Experimental results on both image (MNIST) and tabular (Breast Cancer) datasets show that Metaexplainers consistently outperform individual and state-of-the-art ensemble explanation methods in terms of explanation quality, as measured by established metrics. Tis work paves the way toward more holistic and user-centered AI explainability with a fexible methodology that can be extended to incorporate additional explanation paradigms.