Algorithm for Automatic Legislative Text Consolidation

Matias Etcheverry, Thibaud Real-del-Sarte, Pauline Chavallard


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, finetuned 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 HuggingFace. 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.
Anthology ID:
2024.nllp-1.13
Volume:
Proceedings of the Natural Legal Language Processing Workshop 2024
Month:
November
Year:
2024
Address:
Miami, FL, USA
Editors:
Nikolaos Aletras, Ilias Chalkidis, Leslie Barrett, Cătălina Goanță, Daniel Preoțiuc-Pietro, Gerasimos Spanakis
Venue:
NLLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
166–175
Language:
URL:
https://aclanthology.org/2024.nllp-1.13
DOI:
Bibkey:
Cite (ACL):
Matias Etcheverry, Thibaud Real-del-Sarte, and Pauline Chavallard. 2024. Algorithm for Automatic Legislative Text Consolidation. In Proceedings of the Natural Legal Language Processing Workshop 2024, pages 166–175, Miami, FL, USA. Association for Computational Linguistics.
Cite (Informal):
Algorithm for Automatic Legislative Text Consolidation (Etcheverry et al., NLLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.nllp-1.13.pdf