Metraipolis › archive › dc_edaaa5fb1921
Statutory AI: Aligning Large Language Models With Legal Norms — arXiv:2608.28593
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.28593
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T07:41:33.600Z
- SHA-256 of the archived text
b8b5ba1ee15e45f9d08dd5557c55e3f21aa16e5760bc8949200a8b5f80f476e2- Stable URL of this page
https://metraipolis.com/documento/dc_edaaa5fb1921
How to cite
Statutory AI: Aligning Large Language Models With Legal Norms — arXiv:2608.28593 — arXiv (en), https://arxiv.org/abs/2608.28593 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_edaaa5fb1921 (Metraipolis archive dc_edaaa5fb1921, sha256 b8b5ba1ee15e45f9d08dd5557c55e3f21aa16e5760bc8949200a8b5f80f476e2)
BibTeX
@misc{dcedaaa5fb1921,
title = {Statutory AI: Aligning Large Language Models With Legal Norms — arXiv:2608.28593},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.28593},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_edaaa5fb1921; sha256 b8b5ba1ee15e45f9d08dd5557c55e3f21aa16e5760bc8949200a8b5f80f476e2},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.28593. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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%. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.28593 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T07:28:26.438Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).