The future of human-centric eXplainable Artificial Intelligence (XAI) is not post-hoc explanations
This addresses the problem of unreliable explanations in AI for users in domains like healthcare and education, though it is incremental as it builds on existing critiques of post-hoc methods.
The paper argues that post-hoc explainers for AI systems are insufficient due to systematic disagreements, and proposes a shift towards designing interpretable neural network architectures to meet human-centric needs like real-time and actionable explanations.
Explainable Artificial Intelligence (XAI) plays a crucial role in enabling human understanding and trust in deep learning systems. As models get larger, more ubiquitous, and pervasive in aspects of daily life, explainability is necessary to minimize adverse effects of model mistakes. Unfortunately, current approaches in human-centric XAI (e.g. predictive tasks in healthcare, education, or personalized ads) tend to rely on a single post-hoc explainer, whereas recent work has identified systematic disagreement between post-hoc explainers when applied to the same instances of underlying black-box models. In this paper, we therefore present a call for action to address the limitations of current state-of-the-art explainers. We propose a shift from post-hoc explainability to designing interpretable neural network architectures. We identify five needs of human-centric XAI (real-time, accurate, actionable, human-interpretable, and consistent) and propose two schemes for interpretable-by-design neural network workflows (adaptive routing with InterpretCC and temporal diagnostics with I2MD). We postulate that the future of human-centric XAI is neither in explaining black-boxes nor in reverting to traditional, interpretable models, but in neural networks that are intrinsically interpretable.