A Hypothesis-Driven Approach to Explainable Goal Recognition

In this paper, we introduce an explainable goal-recognition (XGR) approach for decision support that instantiates the evaluative AI paradigm. Current explainable AI (XAI) approaches focus on providing recommendations and justifying those recommendations. However, a shift toward evaluative AI has been proposed, focusing on generating evidence to support or refute human judgments and explaining trade-offs among hypotheses, rather than merely justifying AI recommendations. We introduce such a method for goal recognition tasks by leveraging the Weight of Evidence (WoE) framework. Through a human study in a maritime surveillance task, we demonstrate that our model improves decision accuracy, efficiency, and reliance in complex scenarios, outperforming two baseline models and demonstrating its potential in real-world decision-making.