Directing large language models to follow the letter or spirit of the law

2026-09-19

AI Summary

研究通过定向调整使大型语言模型优先遵循法律的精神或字面意义，以解决机器遵守规则意图的问题，并揭示了模型内部法律概念的几何结构。

Abstract

The distinction between the spirit and letter of the law is a central issue across research and everyday life, and a growing concern for building safe, intelligent machines. What is this distinction based on, and how can we develop machines that follow the intention behind a rule? We used targeted adaptation that made large language models prioritize the spirit or letter of the law. With minimal modifications, our method significantly changed LLM behavior across diverse measures, novel vignettes, real-world scenarios, and influential legal cases. An analysis of model internals revealed a low-dimensional space with three interpretable dimensions matching a formal pre-specified framework for the geometry of legal concepts. These findings show how legal thought in LLMs may be organized and directed.

Problem

• large language models
• letter of the law
• spirit of the law
• legal concepts

Innovation

• targeted adaptation
• spirit or letter of the law
• low-dimensional space
• legal thought