Beyond Binary Moral Judgment: Modeling Ethical Pluralism in AI

2026-05-27

AI Summary

Current approaches to AI moral decision-making often rely on oversimplified judgments, struggling to model the diversity of ethical theories and contextual nuances, thereby limiting explainability and accountability. This work proposes formalizing moral reasoning as a probability distribution over normative ethical theories, constructing an “ethical simplex” that encompasses consequentialism, deontology, virtue ethics, and their 15 subtypes. A dual-stream architecture—integrating normative and semantic pathways—is introduced, leveraging stacked ensembles to fuse semantic context with normative principles. The method offers the first structured representation of ethical pluralism, achieving 88.89% classification accuracy across 450 ethical dilemma cases. Ablation studies demonstrate that the proposed architecture significantly outperforms analogical reasoning, enabling fine-grained moral categorization and robust analysis of ethical disagreement.

Abstract

Critical decision-making in socially consequential spaces is increasingly involving AI systems at varying capacities. Yet, despite the ubiquity of autonomous systems, most approaches to handling autonomous moral decision-making resort to scalar or binary judgments. These methods are insufficient for acceptable moral reasoning, as they provide little explanation, leaving out imperative contextual and theoretical information that must be included to support accountability. For this, we propose a framework to model moral reasoning as a distribution over normative ethical theories or ethical pluralism. We introduce a normative ethics simplex that integrates these theories. A benchmark of 450 cases across 15 fine-grained subtheories was also prepared for the purposes of stacked ensemble learning. These cases describe ethical dilemmas in natural language and have associated extracted contextual features. The implementation of the simplex was achieved via a two-stream normative-semantic architecture. This is followed by the fusion of normative information and a sequential, stacking ensemble to learn the best fit of the three broad theories: consequentialism, virtue ethics, and deontology, and the 15 subcategories. Our experiments demonstrate that the integration of contextual and normative priors with the semantic embeddings significantly improves the performance of the classification, displaying an accuracy of 88.89%. We conducted ablation studies to show that structured ethical representations contribute beyond analogical reasoning, and the chosen stacking architecture gives the best results due to the gradual learning of granularity. Ethical pluralism is also analyzed through entropy, confidence, and visualization. Thus, modeling ethical pluralism as a probabilistic normative distribution supports human-like moral reasoning, ethical disagreement analysis, and future alignment in AI systems.

Problem

• moral judgment
• ethical pluralism
• normative ethics
• AI ethics
• moral reasoning

Innovation

• ethical pluralism
• normative ethics simplex
• stacked ensemble learning
• two-stream normative-semantic architecture
• moral reasoning