Explainable and Human-Grounded AI for Decision Support Systems: The Theory of Epistemic Quasi-Partnerships

TL;DR

This paper proposes the theory of epistemic quasi-partnerships (EQP) to improve explainable AI decision support systems by aligning them with human-grounded explanations like reasons, counterfactuals, and confidence.

Contribution

It introduces the novel EQP theory to better explain empirical findings and guide ethical development of human-centered, explainable AI systems.

Findings

Current explanations do not fully account for trust and accuracy.

The EQP theory explains empirical evidence and ethical considerations.

Adopting the RCC approach enhances human-AI decision support.

Abstract

In the context of AI decision support systems (AI-DSS), we argue that meeting the demands of ethical and explainable AI (XAI) is about developing AI-DSS to provide human decision-makers with three types of human-grounded explanations: reasons, counterfactuals, and confidence, an approach we refer to as the RCC approach. We begin by reviewing current empirical XAI literature that investigates the relationship between various methods for generating model explanations (e.g., LIME, SHAP, Anchors), the perceived trustworthiness of the model, and end-user accuracy. We demonstrate how current theories about what constitutes good human-grounded reasons either do not adequately explain this evidence or do not offer sound ethical advice for development. Thus, we offer a novel theory of human-machine interaction: the theory of epistemic quasi-partnerships (EQP). Finally, we motivate adopting EQP and demonstrate how it explains the empirical evidence, offers sound ethical advice, and entails adopting the RCC approach.