Contrastive Explanations in Quantitative Bipolar Argumentation Frameworks
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…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
