🤖 AI Summary
Current AI decision-support systems over-rely on prescriptive recommendations, undermining users’ autonomous judgment. To address this, we propose a hypothesis-driven Weight-of-Evidence (WoE) explainable AI (XAI) method that refrains from issuing direct recommendations. Instead, given a user-specified hypothesis, it generates and quantifies both supporting and countering evidence. Our key contribution is the first deep integration of the hypothesis-driven paradigm with the WoE framework, establishing a novel non-prescriptive, evidence-centered XAI paradigm. Behavioral experiments and human-AI collaboration evaluations demonstrate that our approach significantly improves decision accuracy and mitigates overreliance on AI. It induces only a marginal increase in underreliance and fundamentally shifts user interaction patterns—from passive “acceptance of recommendations” to active “critical evaluation of evidence.”
📝 Abstract
Prior research on AI-assisted human decision-making has explored several different explainable AI (XAI) approaches. A recent paper has proposed a paradigm shift calling for hypothesis-driven XAI through a conceptual framework called evaluative AI that gives people evidence that supports or refutes hypotheses without necessarily giving a decision-aid recommendation. In this paper, we describe and evaluate an approach for hypothesis-driven XAI based on the Weight of Evidence (WoE) framework, which generates both positive and negative evidence for a given hypothesis. Through human behavioural experiments, we show that our hypothesis-driven approach increases decision accuracy and reduces reliance compared to a recommendation-driven approach and an AI-explanation-only baseline, but with a small increase in under-reliance compared to the recommendation-driven approach. Further, we show that participants used our hypothesis-driven approach in a materially different way to the two baselines.