Explaining Causal Models with Argumentation: the Case of Bi-variate Reinforcement

TL;DR

This paper proposes a novel method to generate argumentation frameworks from causal models to improve explainability in AI, focusing on bi-variate reinforcement, and evaluates their explanatory properties.

Contribution

It introduces a new approach to interpret causal models using argumentation frameworks based on properties of AF semantics, specifically applied to bi-variate reinforcement.

Findings

Argumentative explanations satisfy key explanatory properties

Bipolar AFs effectively represent causal relations

Method enhances interpretability of causal models

Abstract

Causal models are playing an increasingly important role in machine learning, particularly in the realm of explainable AI. We introduce a conceptualisation for generating argumentation frameworks (AFs) from causal models for the purpose of forging explanations for the models' outputs. The conceptualisation is based on reinterpreting desirable properties of semantics of AFs as explanation moulds, which are means for characterising the relations in the causal model argumentatively. We demonstrate our methodology by reinterpreting the property of bi-variate reinforcement as an explanation mould to forge bipolar AFs as explanations for the outputs of causal models. We perform a theoretical evaluation of these argumentative explanations, examining whether they satisfy a range of desirable explanatory and argumentative properties.