Factors are a foundational component of legal analysis and computational models of legal reasoning. These factor-based representations enable lawyers, judges, and AI and Law researchers to reason about legal cases. In this paper, we introduce a methodology that leverages large language models (LLMs) to discover lists of factors that effectively represent a legal domain. Our method takes as input raw court opinions and produces a set of factors and associated definitions. We demonstrate that a semi-automated approach, incorporating minimal human involvement, produces factor representations that can predict case outcomes with moderate success, if not yet as well as expert-defined factors can.
@article{arxiv.2410.07504,
title = {Using LLMs to Discover Legal Factors},
author = {Morgan Gray and Jaromir Savelka and Wesley Oliver and Kevin Ashley},
journal= {arXiv preprint arXiv:2410.07504},
year = {2024}
}