Explaining Arguments' Strength: Unveiling the Role of Attacks and Supports (Technical Report)

TL;DR

This paper introduces Relation Attribution Explanations (RAEs), a novel method using Shapley values to quantify the influence of attacks and supports on argument strength in bipolar argumentation, with applications in fraud detection and language models.

Contribution

It proposes RAEs, a new theory adapting Shapley values for detailed attribution of attack and support roles in argument strength explanations.

Findings

RAEs satisfy several desirable properties.

A probabilistic algorithm efficiently approximates RAEs.

Demonstrated applications in fraud detection and language models.

Abstract

Quantitatively explaining the strength of arguments under gradual semantics has recently received increasing attention. Specifically, several works in the literature provide quantitative explanations by computing the attribution scores of arguments. These works disregard the importance of attacks and supports, even though they play an essential role when explaining arguments' strength. In this paper, we propose a novel theory of Relation Attribution Explanations (RAEs), adapting Shapley values from game theory to offer fine-grained insights into the role of attacks and supports in quantitative bipolar argumentation towards obtaining the arguments' strength. We show that RAEs satisfy several desirable properties. We also propose a probabilistic algorithm to approximate RAEs efficiently. Finally, we show the application value of RAEs in fraud detection and large language models case studies.