CE-QArg: Counterfactual Explanations for Quantitative Bipolar Argumentation Frameworks (Technical Report)

TL;DR

This paper introduces CE-QArg, a novel method for generating counterfactual explanations in Quantitative Bipolar Argumentation Frameworks, enabling users to understand how to modify argument strengths to achieve desired outcomes.

Contribution

It proposes an iterative algorithm for counterfactual explanations in QBAFs, addressing the gap left by attribution-based methods and incorporating polarity and priority modules.

Findings

CE-QArg effectively identifies valid counterfactual explanations.

The method demonstrates formal properties ensuring explanation validity.

Empirical evaluation shows promising results on randomly generated QBAFs.

Abstract

There is a growing interest in understanding arguments' strength in Quantitative Bipolar Argumentation Frameworks (QBAFs). Most existing studies focus on attribution-based methods that explain an argument's strength by assigning importance scores to other arguments but fail to explain how to change the current strength to a desired one. To solve this issue, we introduce counterfactual explanations for QBAFs. We discuss problem variants and propose an iterative algorithm named Counterfactual Explanations for Quantitative bipolar Argumentation frameworks (CE-QArg). CE-QArg can identify valid and cost-effective counterfactual explanations based on two core modules, polarity and priority, which help determine the updating direction and magnitude for each argument, respectively. We discuss some formal properties of our counterfactual explanations and empirically evaluate CE-QArg on randomly generated QBAFs.