Automated Argument Generation from Legal Facts

TL;DR

This paper explores using large language models to automatically generate legal arguments from case facts, aiming to assist legal professionals amid rising case backlogs and limited resources.

Contribution

It introduces a method leveraging open-source large language models for argument generation from legal facts, demonstrating promising overlap with expert annotations.

Findings

Generated arguments have 63% overlap with gold standard annotations.

The approach enhances efficiency in legal case analysis.

Open-source models can effectively assist legal reasoning.

Abstract

The count of pending cases has shown an exponential rise across nations (e.g., with more than 10 million pending cases in India alone). The main issue lies in the fact that the number of cases submitted to the law system is far greater than the available number of legal professionals present in a country. Given this worldwide context, the utilization of AI technology has gained paramount importance to enhance the efficiency and speed of legal procedures. In this study we partcularly focus on helping legal professionals in the process of analyzing a legal case. Our specific investigation delves into harnessing the generative capabilities of open-sourced large language models to create arguments derived from the facts present in legal cases. Experimental results show that the generated arguments from the best performing method have on average 63% overlap with the benchmark set gold standard annotations.