Deep Argumentative Explanations
This work addresses the problem of providing more insightful and transparent explanations for Neural Networks, which is a critical challenge for users who need to understand AI decision-making.
This paper introduces Deep Argumentative eXplanations (DAXs), a novel framework for generating local explanations from Neural Networks that aims to provide transparency into their internal mechanisms. The authors demonstrate DAXs' applicability across various neural architectures and tasks, showing they achieve deep fidelity and low computational cost, and are comprehensible to humans.
Despite the recent, widespread focus on eXplainable AI (XAI), explanations computed by XAI methods tend to provide little insight into the functioning of Neural Networks (NNs). We propose a novel framework for obtaining (local) explanations from NNs while providing transparency about their inner workings, and show how to deploy it for various neural architectures and tasks. We refer to our novel explanations collectively as Deep Argumentative eXplanations (DAXs in short), given that they reflect the deep structure of the underlying NNs and that they are defined in terms of notions from computational argumentation, a form of symbolic AI offering useful reasoning abstractions for explanation. We evaluate DAXs empirically showing that they exhibit deep fidelity and low computational cost. We also conduct human experiments indicating that DAXs are comprehensible to humans and align with their judgement, while also being competitive, in terms of user acceptance, with some existing approaches to XAI that also have an argumentative spirit.