Algorithm for Automatic Legislative Text Consolidation
This work addresses a time-consuming problem for legal professionals by automating legislative text consolidation, though it appears incremental as it applies existing generative techniques to a new domain.
The researchers tackled the problem of automating legislative text consolidation, a traditionally manual legal task, by developing a generative approach using quantized models fine-tuned with LoRA, achieving a success rate of over 63% on a difficult bill and reducing processing time to a few hours.
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.