Kantian-Utilitarian XAI: Meta-Explained
This addresses the problem of making AI-assisted ethical decisions more transparent and actionable for consumers in a specific domain (coffee purchasing), though it appears to be an incremental application of existing ethical frameworks to XAI.
The researchers developed a gamified explainable AI system for ethical consumer decision-making in coffee purchasing that combines Kantian and utilitarian reasoning modules with a meta-explainer to highlight ethical trade-offs and suggest alternatives when welfare loss is minimal.
We present a gamified explainable AI (XAI) system for ethically aware consumer decision-making in the coffee domain. Each session comprises six rounds with three options per round. Two symbolic engines provide real-time reasons: a Kantian module flags rule violations (e.g., child labor, deforestation risk without shade certification, opaque supply chains, unsafe decaf), and a utilitarian module scores options via multi-criteria aggregation over normalized attributes (price, carbon, water, transparency, farmer income share, taste/freshness, packaging, convenience). A meta-explainer with a regret bound (0.2) highlights Kantian--utilitarian (mis)alignment and switches to a deontically clean, near-parity option when welfare loss is small. We release a structured configuration (attribute schema, certification map, weights, rule set), a policy trace for auditability, and an interactive UI.