Generating Case-Based Legal Arguments with LLMs

Abstract

Over its decades long history, the field of AI and Law has made significant progress developing and researching formal models of case based reasoning that are capable of producing legal arguments. These models employ argument schemes to replicate legal argumentation. Although their arguments are accurate and explainable, these systems are costly to produce and maintain, requiring manual case representations and expert-crafted algorithms that mimic argument. To address these limitations we employ a prompt-engineering strategy that leads state-of-the-art LLMs to follow argument schemes. We show that it is feasible for LLMs to produce basic case-based legal arguments.