Contrastive Explanations in Quantitative Bipolar Argumentation Frameworks

2026-09-02

AI Summary

本文通过引入基于移除、梯度和Shapley值的对比归因函数，解决了定量双极论证框架中两个主题论证差异解释的问题。

Abstract

Argumentation frameworks are useful tools for representing and reasoning with information in a variety of settings, e.g. in supplementing AI models as they perform classification tasks, with a notable benefit of providing additional explainability. In this paper, we introduce contrastive explanations for Quantitative Bipolar Argumentation Frameworks (QBAFs), one such formalism. Unlike most existing explanations for QBAFs, which explain the reasoning outcome of a single argument of interest (i.e. a topic argument), contrastive explanations explain the difference between two topic arguments. We introduce a general form of contrastive attribution functions (CAFs) and establish a set of general properties they should satisfy. We introduce CAFs based on removal, gradients and Shapley-values, and study their properties. Finally, to illustrate contrastive explanations, we demonstrate their usefulness in healthcare and bias identification settings.

Problem

• contrastive explanations
• Quantitative Bipolar Argumentation Frameworks (QBAFs)
• topic arguments

Innovation

• contrastive explanations
• Quantitative Bipolar Argumentation Frameworks (QBAFs)
• contrastive attribution functions (CAFs)