ASVRI-Legal: Fine-Tuning LLMs with Retrieval Augmented Generation for Enhanced Legal Regulation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Octadion, One, Prakoso, Bondan Sapta, Setiawan, Nanang Yudi, Yudistira, Novanto
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912688843522048
author Octadion, One
Prakoso, Bondan Sapta
Setiawan, Nanang Yudi
Yudistira, Novanto
author_facet Octadion, One
Prakoso, Bondan Sapta
Setiawan, Nanang Yudi
Yudistira, Novanto
contents In this study, we explore the fine-tuning of Large Language Models (LLMs) to better support policymakers in their crucial work of understanding, analyzing, and crafting legal regulations. To equip the model with a deep understanding of legal texts, we curated a supervised dataset tailored to the specific needs of the legal domain. Additionally, we integrated the Retrieval-Augmented Generation (RAG) method, enabling the LLM to access and incorporate up-to-date legal knowledge from external sources. This combination of fine-tuning and RAG-based augmentation results in a tool that not only processes legal information but actively assists policymakers in interpreting regulations and drafting new ones that align with current needs. The results demonstrate that this approach can significantly enhance the effectiveness of legal research and regulation development, offering a valuable resource in the ever-evolving field of law.
format Preprint
id arxiv_https___arxiv_org_abs_2511_03563
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ASVRI-Legal: Fine-Tuning LLMs with Retrieval Augmented Generation for Enhanced Legal Regulation
Octadion, One
Prakoso, Bondan Sapta
Setiawan, Nanang Yudi
Yudistira, Novanto
Computation and Language
In this study, we explore the fine-tuning of Large Language Models (LLMs) to better support policymakers in their crucial work of understanding, analyzing, and crafting legal regulations. To equip the model with a deep understanding of legal texts, we curated a supervised dataset tailored to the specific needs of the legal domain. Additionally, we integrated the Retrieval-Augmented Generation (RAG) method, enabling the LLM to access and incorporate up-to-date legal knowledge from external sources. This combination of fine-tuning and RAG-based augmentation results in a tool that not only processes legal information but actively assists policymakers in interpreting regulations and drafting new ones that align with current needs. The results demonstrate that this approach can significantly enhance the effectiveness of legal research and regulation development, offering a valuable resource in the ever-evolving field of law.
title ASVRI-Legal: Fine-Tuning LLMs with Retrieval Augmented Generation for Enhanced Legal Regulation
topic Computation and Language
url https://arxiv.org/abs/2511.03563