Using LLMs to Discover Legal Factors

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gray, Morgan, Savelka, Jaromir, Oliver, Wesley, Ashley, Kevin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917799900741632
author Gray, Morgan
Savelka, Jaromir
Oliver, Wesley
Ashley, Kevin
author_facet Gray, Morgan
Savelka, Jaromir
Oliver, Wesley
Ashley, Kevin
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2410_07504
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Using LLMs to Discover Legal Factors
Gray, Morgan
Savelka, Jaromir
Oliver, Wesley
Ashley, Kevin
Computation and Language
Artificial Intelligence
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.
title Using LLMs to Discover Legal Factors
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2410.07504