Nimra Nadeem will present her MSE thesis "Interpretive Discretion in AI Systems" on Wednesday, April 22nd, 2026 in CS 402 and Zoom at 2:00pm. Zoom Link: https://princeton.zoom.us/j/5310001339 Advisor: Peter Henderson Reader: Lydia Liu All are welcome to attend. Abstract: Natural language is inherently ambiguous because it is open to interpretation. Resolving this ambiguity requires the exercise of interpretive discretion: the freedom to choose between multiple plausible interpretations of a given statement. We study this problem in the context of AI alignment. AI systems are increasingly governed by natural language principles, such as OpenAI's ModelSpec or Anthropic's Constitution for Claude. As in legal systems, ambiguity arises both from how principles are written and how they are applied. But while legal systems use institutional safeguards to manage such ambiguity, rule-based AI alignment pipelines lack comparable mechanisms. Drawing on US 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 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, and (2) prompt-based interpretive constraints that reduce disagreement during rule application. We evaluate our framework on a 5,000-scenario subset of the WildChat dataset and show that both interventions improve judgment consistency across a panel of reasonable interpreters. We then extend our analysis to the multi-rule setting and identify some important open challenges. We conclude by discussing the normative implications of interpretive discretion in AI systems, including its impact on fairness in decision-making settings. Our work draws attention to the overlooked challenge of interpretive discretion in AI systems and offers an initial step toward systematically managing it.