AI-Assisted Moot Courts: Simulating Justice-Specific Questioning in Oral Arguments

TL;DR

This paper explores using AI to simulate justice-specific questioning in moot courts, aiming to improve legal training by generating realistic and pedagogically useful oral argument questions.

Contribution

It introduces a novel two-layer evaluation framework and evaluates prompt-based and agentic AI simulators for moot court training.

Findings

AI-generated questions are often realistic according to human judges.

Models achieve high recall of legal issues in questions.

Shortcomings include low diversity and tendency to be sycophantic.

Abstract

In oral arguments, judges probe attorneys with questions about the factual record, legal claims, and the strength of their arguments. To prepare for this questioning, both law schools and practicing attorneys rely on moot courts: practice simulations of appellate hearings. Leveraging a dataset of U.S. Supreme Court oral argument transcripts, we examine whether AI models can effectively simulate justice-specific questioning for moot court-style training. Evaluating oral argument simulation is challenging because there is no single correct question for any given turn. Instead, effective questioning should reflect a combination of desirable qualities, such as anticipating substantive legal issues, detecting logical weaknesses, and maintaining an appropriately adversarial tone. We introduce a two-layer evaluation framework that assesses both the realism and pedagogical usefulness of simulated questions using complementary proxy metrics. We construct and evaluate both prompt-based and agentic oral argument simulators. We find that simulated questions are often perceived as realistic by human annotators and achieve high recall of ground truth substantive legal issues. However, models still face substantial shortcomings, including low diversity in question types and sycophancy. Importantly, these shortcomings would remain undetected under naive evaluation approaches.