AI for Scaling Legal Reform

Legal reform is resource-intensive: implementing changes can require reviewing millions of records to identify outdated provisions. Santa Clara County confronted this problem when California mandated the identification and redaction of racially restrictive covenants across all property records. Drawing on a partnership between Stanford’s RegLab and county officials, the project developed an end-to-end AI pipeline using a fine-tuned language model that substantially outperformed keyword search, achieved near-perfect precision and recall on deed pages, and operated at a small fraction of the cost of proprietary systems. Applied to over 5 million pages of deeds, the system surfaced approximately 7,500 racial covenants and enabled tract-level geospatial analysis. The resulting data revealed distinct temporal waves of covenant use, neighborhood-level clustering, and the dominant role of a small group of developers, with an estimated one in four properties subject to racial covenants by 1950. The work illustrates how AI can scale legal clean-up while preserving counsel-led review.

Mirac Suzgun is a Ph.D. candidate in Computer Science at Stanford University, co-advised by Professors Dan Jurafsky and James Zou, and a J.D. candidate at Stanford Law School. His research examines the capabilities and limitations of modern language models, focusing on reasoning, hallucination detection and mitigation, and societal applications. He also conducts legal scholarship on constitutional law, administrative law, and AI governance and regulatory policy, and works closely with Professor Daniel E. Ho at the Stanford RegLab. He graduated from Harvard College with a joint degree in Mathematics and Computer Science and a secondary field in Folklore & Mythology, receiving the Thomas T. Hoopes Prize for his undergraduate thesis. His work has appeared in leading venues including Nature Machine Intelligence, The Lancet Digital Health, Journal of Legal Analysis, Journal of Empirical Legal Studies, ACL, EMNLP, ICLR, and NeurIPS. He has worked at Google Brain, Microsoft Research, Meta's GenAI/Llama team, and OpenEvidence, and has served as a legal intern at the Administrative Conference of the United States and as a litigation summer associate at WilmerHale. His graduate studies have been supported by the Google Ph.D. Fellowship, Stanford HAI-SAP Fellowship, and Stanford Law School Fellowship.