Advancing Interactive Explainable AI via Belief Change Theory
This work addresses the problem of enhancing interactivity and accountability in explainable AI for users of complex AI systems, though it appears incremental as it builds on existing belief change theory.
The paper tackles the need for more interactive explainable AI by proposing belief change theory as a formal foundation to incorporate user feedback into logical representations of classifiers, aiming to provide a principled framework for developing interactive explanations with warranted behavior and transparency.
As AI models become ever more complex and intertwined in humans' daily lives, greater levels of interactivity of explainable AI (XAI) methods are needed. In this paper, we propose the use of belief change theory as a formal foundation for operators that model the incorporation of new information, i.e. user feedback in interactive XAI, to logical representations of data-driven classifiers. We argue that this type of formalisation provides a framework and a methodology to develop interactive explanations in a principled manner, providing warranted behaviour and favouring transparency and accountability of such interactions. Concretely, we first define a novel, logic-based formalism to represent explanatory information shared between humans and machines. We then consider real world scenarios for interactive XAI, with different prioritisations of new and existing knowledge, where our formalism may be instantiated. Finally, we analyse a core set of belief change postulates, discussing their suitability for our real world settings and pointing to particular challenges that may require the relaxation or reinterpretation of some of the theoretical assumptions underlying existing operators.