Alignment as Jurisprudence

Nicholas Caputo

arXiv:2605.08416 · 2026-05-12 공개 · arXiv · PDF

alignment case-based-reasoning jurisprudence constitutional-ai interpretivism legal-theory ai-empowerment rule-based-systems

Abstract

Jurisprudence, the study of how judges should properly decide cases, and alignment, the science of getting AI models to conform to human values, share a fundamental structure. These seemingly distant fields both seek to predict and shape how decisions by powerful actors, in one case judges and in the other increasingly powerful artificial intelligences, will be made in the unknown future. And they use similar tools of the specification and interpretation of language to try to accomplish those goals. The great debates of jurisprudence, about what the law is and what it should be, can provide insight into alignment, and lessons from what does and does not work in alignment can help make progress in jurisprudence. This essay puts the two fields directly into conversation. Drawing on leading accounts of jurisprudence, particularly Dworkin's principle-oriented interpretivism and Sunstein's positivist account of law as analogical reasoning, and on cutting-edge alignment approaches, namely Constitutional AI and case-based reasoning, it illustrates the value of a more sophisticated legally-inspired approach to the interplay of rules and cases in finetuning alignment and points to ways that AI can provide a better understanding of how the law works and how it can be improved by the introduction of AI. AI systems and the law should operate to empower people to act in the world, helping to expand their capabilities and the extent to which they are able to achieve their goals. As AI continues to improve in capacity, and as the constraints that legal theory places on human judges seem be coming undone, the conversation between these two fields will become increasingly essential and may help point to a better version of both.

한국어 요약

📋 한 줄 요약

**[AI Alignment / Legal Theory]** AI 정렬 문제를 법학(jurisprudence)의 관점에서 재해석하고, Dworkin·Sunstein 같은 법이론과 Constitutional AI·case-based reasoning을 직접 대비시키는 에세이.

🎯 핵심 기여도

💡 핵심 아이디어

판사가 법을 어떻게 결정해야 하는지에 대한 법학적 논쟁은, AI를 어떻게 인간 가치에 부합시킬 것인가에 대한 정렬 논쟁과 동형적이다. 두 분야 모두 언어의 명세와 해석이라는 동일한 도구를 사용한다.

🔬 기술적 접근법

📊 주요 결과

💭 의의 및 한계

**의의**: AI 안전 연구자와 법학자 사이의 학제 간 대화를 위한 구체적 어휘와 프레임을 제공한다. **한계**: 정량적 실험이나 측정 지표가 없는 개념적 에세이로, 실제 정렬 알고리즘 개선으로 이어지려면 추가 구현이 필요하다.

🚀 실용적 활용