Towards the new XAI: A Hypothesis-Driven Approach to Decision Support Using Evidence

📅 2024-02-02
🏛️ European Conference on Artificial Intelligence
📈 Citations: 5
Influential: 1
📄 PDF
🤖 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.”

Technology Category

Application Category

📝 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.
Problem

Research questions and friction points this paper is trying to address.

Improving AI-supported decision-making with hypothesis-driven models
Extending Weight of Evidence framework for tabular and image data
Evaluating decision-support approaches in housing and medical domains
Innovation

Methods, ideas, or system contributions that make the work stand out.

Extends Weight of Evidence framework implementation
Supports both tabular and image data processing
Provides evidence for or against hypotheses
The University of Melbourne | The University of Queensland | CSIRO’s Data61
T
Thao Le
School of Computing and Information Systems, The University of Melbourne, Australia
T
Tim Miller
School of Electrical Engineering and Computer Science, The University of Queensland, Australia
R
Ronal Singh
CSIRO’s Data61, Australia
L
L. Sonenberg
School of Computing and Information Systems, The University of Melbourne, Australia