Disentangling AI Alignment: A Structured Taxonomy Beyond Safety and Ethics

TL;DR

This paper proposes a structured taxonomy for AI alignment, clarifying the conceptual boundaries among safety, ethics, legality, and other goals to guide interdisciplinary research and practical implementation.

Contribution

It introduces a comprehensive taxonomy that distinguishes alignment aims, scope, and constituency, offering a foundational framework for integrating diverse AI alignment perspectives.

Findings

Reveals multiple legitimate alignment configurations

Provides a structured framework for understanding AI alignment

Clarifies the relationship between safety, ethics, and legality

Abstract

Recent advances in AI research make it increasingly plausible that artificial agents with consequential real-world impact will soon operate beyond tightly controlled environments. Ensuring that these agents are not only safe but that they adhere to broader normative expectations is thus an urgent interdisciplinary challenge. Multiple fields -- notably AI Safety, AI Alignment, and Machine Ethics -- claim to contribute to this task. However, the conceptual boundaries and interrelations among these domains remain vague, leaving researchers without clear guidance in positioning their work. To address this meta-challenge, we develop a structured conceptual framework for understanding AI alignment. Rather than focusing solely on alignment goals, we introduce a taxonomy distinguishing the alignment aim (safety, ethicality, legality, etc.), scope (outcome vs. execution), and constituency (individual vs. collective). This structural approach reveals multiple legitimate alignment configurations, providing a foundation for practical and philosophical integration across domains, and clarifying what it might mean for an agent to be aligned all-things-considered.