The Free Law Project recently announced its intention to build a citator using AI.
If successful, the emergence of an open-access, open-source legal citator would be significant to both practitioners and the public. Citators, such as Shepard’s and KeyCite, answer the foundational question of whether the case law you are using is good law, bad law, or somewhere in between. FLP’s mission is to “democratize access to this crucial information for small law firms, independent researchers, self-represented litigants, and anyone interested in understanding legal precedent.”
FLP has broken down the work of creating a citator into smaller, more manageable strategic parts. “Our initial focus is on identifying AI systems capable of understanding complex legal language and the often subtle indicators of how one legal decision treats another.”
To establish proof of concept, they started with the question: Can AI accurately identify when a Supreme Court opinion overrules another Supreme Court opinion?
“To a human, this seems straightforward, but in the text of a decision, a citation can take many forms,” notes FLP. Using a wide spectrum of AI models, they conducted a series of advanced prompting to identify the best language and techniques to include.
The early results of which AI models proved to be most capable are included in the article’s final paragraphs. As FLP notes, “This progress report represents merely the first step in our ambitious journey toward building a comprehensive legal citator.”
by Eric Taylor, Evening Reference Librarian