Guardado en:
Detalles Bibliográficos
Autores principales: Etcheverry, Matias, Real, Thibaud, Chavallard, Pauline
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2501.16794
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912207073181696
author Etcheverry, Matias
Real, Thibaud
Chavallard, Pauline
author_facet Etcheverry, Matias
Real, Thibaud
Chavallard, Pauline
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2501_16794
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Algorithm for Automatic Legislative Text Consolidation
Etcheverry, Matias
Real, Thibaud
Chavallard, Pauline
Computation and Language
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.
title Algorithm for Automatic Legislative Text Consolidation
topic Computation and Language
url https://arxiv.org/abs/2501.16794