Research
AI and the Law
- “Bye-bye, Bluebook? Automating Legal Drudgery With AI-Augmented Rule Following.” mimeo (with Eric Martínez). We show that off-the-shelf LLMs produce fully compliant Bluebook citations less than half of the time, cautioning against the use of such models to automate aspects of the law where fidelity to detail is paramount.
- “Hallucination-Free? Assessing the Reliability of Leading AI Legal Research Tools.” 2025. Journal of Empirical Legal Studies 22(2): 216-242 (with Varun Magesh, Faiz Surani, Mirac Suzgun, Christopher D. Manning, and Daniel E. Ho). We demonstrate the distinctive challenges that retrieval-agumented generation (RAG) faces in the legal domain, revealing the need for transparent benchmarking of commercially available legal AI products.
- “Large Legal Fictions: Profiling Legal Hallucinations in Large Language Models.” 2024. Journal of Legal Analysis 16(1): 64-93 (with Varun Magesh, Mirac Suzgun, and Daniel E. Ho). We show that popular AI tools like ChatGPT frequently “hallucinate,” or invent, false information about American case law, calling into question their ability to democratize access to justice.
Judicial Behavior and Discrimination
- “What Can We Learn About Discrimination From Random Judicial Assignment?” mimeo. I precisely describe the empirical quantities that can (and those that cannot) be identified from random judicial assignment, providing new evidence for the sources of discrimination in the judiciary.
- “The Dogma Within? Examining Religious Bias in Private Title VII Claims.” 2021. Journal of Empirical Legal Studies 18(4): 742-764 (with Devan N. Patel and Matthew E.K. Hall). Examining an original dataset of private discrimination claims, we question the popular belief that judges’ religions cause them to decide cases in a distinctive way.
Methodology
- “You Don’t Have a Selection Problem: We Live in a Selectiony World.” 2026. Annual Review of Law and Social Science 22: 73-90 (with Issa Kohler-Hausmann). Reviewing the causal revolution in empirical legal studies, we provide a conceptual framework for diagnosing threats to inference that arise when the definition of a causal treatment (e.g., conviction, bail, liability) is itself imbued with certain reasons or selection processes, which we argue happens frequently in law.
- “Chain Novel, or Markov Chain? Estimating the Authority of U.S. Supreme Court Case Law.” 2024. Journal of Empirical Legal Studies 21(4): 861-898. I show how modeling the network of U.S. Supreme Court case law as a Markov chain unlocks an intuitive estimator of case authority that outperforms existing approaches in a variety of validation tasks.
- “Eyecite: A Tool for Parsing Legal Citations.” 2021. Journal of Open Source Software 6(66): 3617 (with Jack Cushman and Michael Lissner). We open-source a highly performant engine for the extraction and aggregation of legal citations, trained and deployed on the datasets of the Free Law Project and the Caselaw Access Project.
Other Writing