AI-Assisted Moot Courts
Empirical data, an eval suite, and reflections on the future.
Cross-posted from the CITP blog and written by: Kylie Zhang, Nimra Nadeem, Dominik Stammbach, Lucia Zheng, and Peter Henderson.
In a recent TED Talk, Supreme Court attorney Neal Katyal describes how he prepared for his Supreme Court oral arguments in Learning Resources v. Trump, the 2025 tariffs case. Katyal says that he was guided in his journey by four mentors: sports coach Bob, improv coach Liz, “relentless” legal coach Harvey, and meditation coach Ben. Then comes the plot twist: Harvey is actually AI. “I trained it on every question asked by a Supreme Court justice in the last 25 years and everything they’ve written… And in that, patterns emerged. It predicted the contours of the very argument I would face,” Katyal proclaims. Startling and futuristic, Katyal’s speech positions AI as a revolutionary force for oral argument preparation. But does AI as an oral argument simulator live up to the hype?
Measuring the usefulness of AI-assisted oral argument simulators
In our recent paper, we present the first comprehensive framework for evaluating AI as a practice partner for oral argument preparation. Given the facts of the case, the legal question, and the oral argument so far, the AI-simulator is tasked with predicting what a specific justice would say next. We construct our task samples using U.S. Supreme Court oral argument transcripts and test both prompt-based and agentic simulators built on top of open and closed source frontier models.
Our evaluation framework combines 20 different metrics to assess the realism and pedagogical usefulness of these AI-generated justice questions. These metrics include whether the simulated questions cover key legal issues, the diversity of question types, the robustness of the simulators against adversarial advocate behavior, and human evaluation of realism.
Given the facts of the case, legal question, and transcript of an oral argument up to a turn, our AI-simulator predicts what a specific justice would say. We then measure the realism and pedagogical usefulness of these AI-generated questions.
The Upside: Many models do quite well in issue coverage!
In line with Katyal’s praises, we found that the best AI simulators actually perform surprisingly well. Human evaluators, including law students, found simulated questions to be very realistic, and often they rated them equally as compelling to actual justice responses. Most models were strong at detecting logical fallacies (over 80% detection rate for seven out of ten tested categories) and were able to broadly address more than 60% of the legal issues raised by actual SCOTUS justices during oral arguments. The latter finding lends credence to claims made by Katyal’s slides, where he compared Harvey’s outputs to what an actual justice said in his case.
The Downside: Models are still too sycophantic and miss key issues.
But we also found very significant shortcomings. For one, AI simulators were extremely sycophantic and, as a result, performed very poorly on our adversarial tests.
When attorneys deliberately broke courtroom decorum, even the best simulators pushed back less than 40% of the time. When presented with political rage-bait provocations or arguments that switched sides mid-stream, detection rates dropped below 10%.
In other words, most models fail to call out an advocate for abandoning their argument for their opponent’s in the middle of questioning! Such pushback requires models to disagree with the user, which post-training on human preferences tends to discourage. Real justices readily, and sometimes aggressively, challenge inconsistencies in advocates’ claims. So, an advocate only using an AI legal coach may not be well prepared for that pressure, and may instead erroneously assume that certain problematic behavior is acceptable. Such sycophantic tendencies also imply broader challenges about AI use in pedagogical settings, where it is important to give critical feedback and avoid reinforcing errors.
We also found that AI-generated questions were much less diverse than the types of questions asked by real-world justices. For example, AI simulators almost never ask hypothetical questions. Using hypotheticals to probe an advocate’s argument is common among justices, most notably former SCOTUS Justice Stephen Breyer. Generating good hypotheticals requires understanding the decision boundary the advocate is proposing and constructing fact patterns that test counterfactual worlds. But current models struggle with this kind of analytical creativity.
Also, despite their ability to broadly cover key legal issues (as noted above), when we assessed whether the simulated questions covered the fine-grained details of legal issues raised by real-world justices, we found that even the best model was only able to cover at most 41% of the issues. This finding is in line with Josh Blackman’s critique that many Harvey outputs are only topically related to actual questions asked and fail to capture their full scope and breadth.
Models can be sycophantic – the left (in grey) shows the text of the actual turn while the right (in color) shows an adversarial test. GPT4o ignores the adversarial behavior, which is problematic because actual justices would call it out.
Thoughts on the future of AI thought partners for high-stakes oral arguments
We started this line of research because we envision a world with equitable, open, and accessible tools to help improve the status quo in oral argument preparation. While wealthy firms can afford to hire former judges for moot courts, under-resourced attorneys don’t have such luxuries. And because so much of appellate preparation turns on strategizing about how to frame a case in response to these types of questions and get at the heart of lawyering, effective AI sparring partners would meaningfully expand how advocates can prepare effectively for oral arguments.
Our results suggest that while AI for oral argument practice shows significant promise, more research is needed to address substantial limitations like sycophantic behavior. Like Katyal, we agree that Harvey and other legal AI tools are “not some god” but can make for valuable thought partners. But to make good use of this potential, we need a nuanced and thoughtful approach to both training, evaluation, and marketing. Publicizations of shortcomings, in particular, can allow users to adjust their AI usage to avoid known system limitations, which is especially important in high-stakes settings. We hope that researchers and model developers continue to invest in such use cases in order to turn current systems into reliable thought partners that offer constructive critique and help develop - rather than replace - human reasoning.
(For more details on the paper, we also wrote up an interactive webpage, which you can find here. Note: we have some nice interactive components on the website, including a quiz to see if you can guess the real justice’s question or the AI generated questions! Check it out!)