Statutory Construction and Interpretation for Artificial Intelligence
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911132134932480 |
|---|---|
| author | He, Luxi Nadeem, Nimra Liao, Michel Chen, Howard Chen, Danqi Cuéllar, Mariano-Florentino Henderson, Peter |
| author_facet | He, Luxi Nadeem, Nimra Liao, Michel Chen, Howard Chen, Danqi Cuéllar, Mariano-Florentino Henderson, Peter |
| contents | AI systems are increasingly governed by natural language principles, yet a key challenge arising from reliance on language remains underexplored: interpretive ambiguity. As in legal systems, ambiguity arises both from how these principles 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, AI alignment pipelines offer no comparable protections. Different interpretations of the same rule can lead to inconsistent or unstable model behavior. Drawing on legal theory, we identify key gaps in current 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 mirrors two legal 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 inconsistency in 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 first step toward systematically managing interpretive ambiguity, an essential step for building more robust, law-following AI systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_01186 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Statutory Construction and Interpretation for Artificial Intelligence He, Luxi Nadeem, Nimra Liao, Michel Chen, Howard Chen, Danqi Cuéllar, Mariano-Florentino Henderson, Peter Computation and Language Artificial Intelligence Computers and Society AI systems are increasingly governed by natural language principles, yet a key challenge arising from reliance on language remains underexplored: interpretive ambiguity. As in legal systems, ambiguity arises both from how these principles 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, AI alignment pipelines offer no comparable protections. Different interpretations of the same rule can lead to inconsistent or unstable model behavior. Drawing on legal theory, we identify key gaps in current 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 mirrors two legal 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 inconsistency in 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 first step toward systematically managing interpretive ambiguity, an essential step for building more robust, law-following AI systems. |
| title | Statutory Construction and Interpretation for Artificial Intelligence |
| topic | Computation and Language Artificial Intelligence Computers and Society |
| url | https://arxiv.org/abs/2509.01186 |