Research
Our research is focused on the intersection of law, technology, and AI. We are particularly interested in the application of data science and machine learning to legal data, including public law like case law, dockets, statutes, regulation and private law like contracts, policies and procedures, and corporate filings.
AI and the Bar Exam
"AGI" and the future of law
What is "AGI" capable of - today, in the near future, and over the medium term?
In this research agenda, we frame the capabilities of AGI in the context of a well-known assessment of legal reasoning: the bar exam. Our ground-breaking research documents that, for the first time ever, state-of-the-art models can pass the exam.
The implications for all buyers and sellers of legal services are nothing short of profound.
Litigation Prediction
Forecasting Supreme Court decisions
How can machine learning and natural language processing be used to help first- and third parties predict the outcome of litigation?
In this research agenda, we apply ensemble machine learning techniques to prediction the votes of individual Supreme Court Justices and the Court as a whole over 200 years.
Regulatory dynamics and monitoring
How and where is the law changing?
Organizations around the world are increasingly subject to a complex web of regulations. How can we use machine learning and natural language processing to help organizations understand and monitor the regulatory landscape?
In this research agenda, we apply machine learning and natural language processing to the task of measuring and modeling the regulatory ecosystem. In numerous publications, we evaluate the source of regulations in the US Code, the Code of Federal Regulations, the Federal Register, and various foreign sources. We also examine the filings of publicly-traded and registered entities to identify which laws and rules are actually experienced as material risks or opportunities.
Our findings and techniques have direct relevance to organizations who monitor and manage complex regulatory environments, especially in the financial services and manufacturing industries.
Legal Natural Language Processing (NLP)
Information extraction and classification for legal text
Legal language is unique and complex. Yet legal and financial documents often include critically important information for decision-making in organizations.
In this research agenda, we develop and assess natural language software and techniques to aid in the industrial use of such technology for the search, extraction, and analysis of legal documents.
Our findings and software have been used by thousands of individuals and organizations around the world and cited in hundreds of publications.