A Causal Argumentation Method for Explainability of Machine Learning Models
For XAI researchers, it offers a novel approach to generate causal explanations, but the evaluation is limited and incremental over existing methods.
The paper introduces a method combining causal discovery with bipolar argumentation to explain why machine learning models make predictions, tested on two benchmark datasets.
Explainable AI (XAI) methods identify which features are relevant to a model's predictions but often fail to clarify why certain decisions are made. In this work, we present a novel method that integrates causality with argument-based reasoning to explain why models may be making predictions. Our approach first identifies causal relationships among variables using causal discovery methods and then translates these into a Bipolar Argumentation Framework (BAF) to represent supportive and opposing interactions among features. By using semi-stable semantics, we find extensions of features that explain why certain outcomes may have been chosen. We demonstrate our method on two benchmark datasets and compare its results against standard post-hoc explainability approaches.