CoAX: Cognitive-Oriented Attribution eXplanation User Model of Human Understanding of AI Explanations
For XAI researchers, this work provides a cognitive modeling approach to debug and improve human understanding of AI explanations, addressing a known bottleneck in XAI effectiveness.
The paper investigates why users struggle to effectively use AI explanations by modeling human reasoning strategies for XAI methods on tabular data. Their cognitive models better fit human decisions than baseline ML proxies, enabling hypothesis testing without costly human studies.
Explainable AI (XAI) aims to improve user understanding and decisions when using AI models. However, despite innovations in XAI, recent user evaluations reveal that this goal remains elusive. Understanding human cognition can help explain why users struggle to effectively use AI explanations. Focusing on reasoning on structured (tabular) data, we examined various reasoning strategies for different XAI methods (none, feature importance, feature attribution) in the decision task of anticipating AI decisions (i.e., forward simulation). We i) elicited reasoning strategies from a formative user study, and ii) collected decisions from a summative user study. Using cognitive modeling, we implemented the processes underlying each reasoning strategy and evaluated their alignment with human decision-making. We found that our models better fit human decisions than baseline machine learning proxies, providing insights into which reasoning strategies are (in)effective. We then demonstrate how the fitted model can be used to form hypotheses and investigate research questions that are costly to study with real human participants. This work contributes to debugging human understanding of XAI, informing the future development of more usable and interpretable AI explanations.