Recent advances in artificial intelligence (AI) have underscored the need for explainable AI (XAI) to support human understanding of AI systems. Consideration of human factors that impact explanation efficacy, such as mental workload and human understanding, is central to effective XAI design. Existing work in XAI has demonstrated a tradeoff between understanding and workload induced by different types of explanations. Explaining complex concepts through abstractions (hand-crafted groupings of related problem features) has been shown to effectively address and balance this workload-understanding tradeoff. In this work, we characterize the workload-understanding balance via the Information Bottleneck method: an information-theoretic approach which automatically generates abstractions that maximize informativeness and minimize complexity. In particular, we establish empirical connections between workload and complexity and between understanding and informativeness through human-subject experiments. This empirical link between human factors and information-theoretic concepts provides an important mathematical characterization of the workload-understanding tradeoff which enables user-tailored XAI design.

翻译：人工智能的最新进展凸显了解释性人工智能（XAI）支持人类理解AI系统的必要性。考虑影响解释效能的人因因素（如脑力工作量和人类理解）是有效XAI设计的核心。现有XAI研究表明，不同类型的解释会产生理解与工作量之间的权衡。通过抽象（即对相关问题特征进行人工分组）来解释复杂概念，已被证明能有效应对并平衡这种工作量-理解权衡。本研究利用信息瓶颈方法对工作量-理解平衡进行表征：这是一种信息论方法，可自动生成兼顾信息最大化与复杂度最小化的抽象。具体而言，我们通过人类受试者实验建立了工作量与复杂度之间的实证联系，以及理解与信息量之间的实证联系。人因因素与信息论概念之间的这种实证关联，为工作量-理解权衡提供了重要的数学表征，从而支持用户定制化的XAI设计。