Explaining Arguments' Strength: Unveiling the Role of Attacks and Supports (Technical Report)
This work addresses the need for fine-grained explanations in argumentation frameworks, particularly for domains like fraud detection, though it appears incremental by building on existing attribution methods.
The paper tackles the problem of quantitatively explaining argument strength in bipolar argumentation by introducing Relation Attribution Explanations (RAEs), which adapt Shapley values to attribute scores to attacks and supports, and demonstrates their application in fraud detection and large language models.
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.