Algorithm for Automatic Legislative Text Consolidation

TL;DR

This paper presents a novel generative model-based method for automating legislative text consolidation, significantly improving efficiency and enabling rapid updates to legal documents, with a success rate over 63%.

Contribution

First application of generative models to legislative text consolidation, introducing a fine-tuned light quantized model with LoRA for accurate amendments.

Findings

Automated pipeline completes consolidation in hours.

Achieved over 63% success rate on complex bills.

Significant efficiency improvements demonstrated.

Abstract

This study introduces a method for automating the consolidation process in a legal context, a time-consuming task traditionally performed by legal professionals. We present a generative approach that processes legislative texts to automatically apply amendments. Our method employs light quantized generative model, fine-tuned with LoRA, to generate accurate and reliable amended texts. To the authors knowledge, this is the first time generative models are used on legislative text consolidation. Our dataset is publicly available on HuggingFace1. Experimental results demonstrate a significant improvement in efficiency, offering faster updates to legal documents. A full automated pipeline of legislative text consolidation can be done in a few hours, with a success rate of more than 63% on a difficult bill.