Statutory AI: Aligning Large Language Models With Legal Norms

Researchers propose Statutory AI, a hybrid approach that uses legal texts as a constitutional framework to align large language models with legal norms, reducing harmful content by 52 to 59 percentage points across tested models, about 10 percentage points higher than standard Constitutional AI, while cutting computation time by over 50%. The method operates in two stages using Chain-of-Thought prompting, classifying user prompts into themes and analyzing them with relevant legal articles, as demonstrated in an experiment with 1,000 red-teaming prompts and five penal themes.

arXiv:2608.28593v1 Announce Type: new Abstract: With the increasing development of AI regulatory frameworks, ensuring that artificial intelligence systems, particularly generative models, operate in accordance with legal and ethical standards has become a critical priority. Existing proposals for AI alignment and value-guided behavior, however, face some limitations. Approaches such as Constitutional AI depend on human supervision, while broad normative frameworks like the Good-for-Humanity GfH principle may be overly general and ambiguous to provide actionable governance guidance. To overcome these limitations, we propose a hybrid approach called Statutory AI that employs pre-existing human-authored principles drawn from specific themes within a legal corpus. Specifically, Statutory AI uses legal texts as a constitutional framework, enabling AI systems to autonomously critique and revise their outputs according to established norms. It operates in two stages, both using Chain-of-Thought prompting. The first stage classifies the user prompt into one of the identified themes, while the second stage analyzes it in conjunction with relevant articles selected from the legal corpus of that theme. To illustrate the potential of our approach, we conducted an experiment involving 1,000 red-teaming prompts and five penal themes: discrimination, disclosure of confidential information, violence, fraud, and abuse of vulnerable persons. Statutory AI reduced harmful content by 52 to 59 percentage points across tested models, approximately 10 percentage points higher than standard Constitutional AI, while cutting computation time by over 50%.