EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Statutory construction and interpretation for AI

Luxi He, Nimra Nadeem iD, Michel Liao iD, Howard Chen, Danqi Chen, Mariano-Florentino Cuéllar, Peter Henderson iD

Proceedings of the National Academy of Sciences · 28.07.2026 · 123 (30)

DOI: 10.1073/pnas.2509766123 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the National Academy of Sciences, online erschienen am 20.07.2026. Verfasst von Luxi He und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, Princeton University, Princeton, NJ 08540. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 69 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

AI systems are increasingly governed by natural language rules, yet a key challenge arising from reliance on language remains underexplored: interpretive ambiguity. As in legal systems, ambiguity arises both from how these rules are written and how they are applied. But while legal systems use institutional safeguards to manage such ambiguity, such as transparent appellate review policing interpretive constraints, rule-based AI alignment pipelines lack comparable protections. Different interpretations of the same rule can lead to inconsistent model behavior. Drawing on U.S. legal theory, we identify key gaps in current rule-based alignment pipelines by examining how legal systems constrain ambiguity at both the rule creation and rule application steps. We then propose a computational framework that formalizes interpretive ambiguity as constrained entropy minimization and introduces two law-inspired mechanisms: 1) a rule refinement pipeline that minimizes interpretive disagreement by revising ambiguous rules (analogous to agency rulemaking or iterative legislative action), and 2) prompt-based interpretive constraints that reduce disagreement during rule application (analogous to legal canons that guide judicial discretion). We evaluate our framework on a 5,000-scenario subset of the WildChat dataset and show that both interventions significantly improve judgment consistency across a panel of reasonable interpreters. Our approach offers a step toward systematically managing interpretive ambiguity, an essential step for building more robust, law-following AI systems.

Schlagwörter

Stichwörter der Autor:innen

AIalignmentlaw

Autor:innen und Institutionen

  • Department of Computer Science, Princeton University, Princeton, NJ 08540.
  • Carnegie Endowment for International Peace, Washington, DC 20036.

ORCID-Profile: Nimra Nadeem, Michel Liao, Peter Henderson

Zitieren

APA

He, L., Nadeem, N., Liao, M., Chen, H., Chen, D., Cuéllar, M. F., & Henderson, P. (2026). Statutory construction and interpretation for AI. Proceedings of the National Academy of Sciences, 123(30). https://doi.org/10.1073/pnas.2509766123

Vancouver

He L, Nadeem N, Liao M, Chen H, Chen D, Cuéllar MF, et al. Statutory construction and interpretation for AI. Proceedings of the National Academy of Sciences. 2026;123(30). doi:10.1073/pnas.2509766123

BibTeX
@article{He2026,
  author = {He, Luxi and Nadeem, Nimra and Liao, Michel and Chen, Howard and Chen, Danqi and Cuéllar, Mariano-Florentino and Henderson, Peter},
  title = {Statutory construction and interpretation for AI},
  journal = {Proceedings of the National Academy of Sciences},
  year = {2026},
  volume = {123},
  number = {30},
  doi = {10.1073/pnas.2509766123}
}
Kostenlos starten →