English

A Causal Argumentation Method for Explainability of Machine Learning Models

Artificial Intelligence 2026-05-22 v1

Abstract

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.

Keywords

Cite

@article{arxiv.2605.21758,
  title  = {A Causal Argumentation Method for Explainability of Machine Learning Models},
  author = {Henry Salgado and Meagan R. Kendall and Martine Ceberio},
  journal= {arXiv preprint arXiv:2605.21758},
  year   = {2026}
}

Comments

To be published in The 4th World Conference on eXplainable Artificial Intelligence