An Information Bottleneck Characterization of the Understanding-Workload Tradeoff
This work addresses the problem of designing effective XAI systems for users by providing a mathematical framework to tailor explanations, though it is incremental as it builds on existing abstraction-based methods.
The paper tackles the tradeoff between human understanding and mental workload in explainable AI (XAI) by characterizing it using the Information Bottleneck method, which automatically generates abstractions to balance informativeness and complexity, with empirical validation through human-subject experiments linking workload to complexity and understanding to informativeness.
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.