LegalRAG: A Hybrid RAG System for Multilingual Legal Information Retrieval

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kabir, Muhammad Rafsan, Sultan, Rafeed Mohammad, Rahman, Fuad, Amin, Mohammad Ruhul, Momen, Sifat, Mohammed, Nabeel, Rahman, Shafin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913804161384448
author Kabir, Muhammad Rafsan
Sultan, Rafeed Mohammad
Rahman, Fuad
Amin, Mohammad Ruhul
Momen, Sifat
Mohammed, Nabeel
Rahman, Shafin
author_facet Kabir, Muhammad Rafsan
Sultan, Rafeed Mohammad
Rahman, Fuad
Amin, Mohammad Ruhul
Momen, Sifat
Mohammed, Nabeel
Rahman, Shafin
contents Natural Language Processing (NLP) and computational linguistic techniques are increasingly being applied across various domains, yet their use in legal and regulatory tasks remains limited. To address this gap, we develop an efficient bilingual question-answering framework for regulatory documents, specifically the Bangladesh Police Gazettes, which contain both English and Bangla text. Our approach employs modern Retrieval Augmented Generation (RAG) pipelines to enhance information retrieval and response generation. In addition to conventional RAG pipelines, we propose an advanced RAG-based approach that improves retrieval performance, leading to more precise answers. This system enables efficient searching for specific government legal notices, making legal information more accessible. We evaluate both our proposed and conventional RAG systems on a diverse test set on Bangladesh Police Gazettes, demonstrating that our approach consistently outperforms existing methods across all evaluation metrics.
format Preprint
id arxiv_https___arxiv_org_abs_2504_16121
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LegalRAG: A Hybrid RAG System for Multilingual Legal Information Retrieval
Kabir, Muhammad Rafsan
Sultan, Rafeed Mohammad
Rahman, Fuad
Amin, Mohammad Ruhul
Momen, Sifat
Mohammed, Nabeel
Rahman, Shafin
Information Retrieval
Computation and Language
Machine Learning
Natural Language Processing (NLP) and computational linguistic techniques are increasingly being applied across various domains, yet their use in legal and regulatory tasks remains limited. To address this gap, we develop an efficient bilingual question-answering framework for regulatory documents, specifically the Bangladesh Police Gazettes, which contain both English and Bangla text. Our approach employs modern Retrieval Augmented Generation (RAG) pipelines to enhance information retrieval and response generation. In addition to conventional RAG pipelines, we propose an advanced RAG-based approach that improves retrieval performance, leading to more precise answers. This system enables efficient searching for specific government legal notices, making legal information more accessible. We evaluate both our proposed and conventional RAG systems on a diverse test set on Bangladesh Police Gazettes, demonstrating that our approach consistently outperforms existing methods across all evaluation metrics.
title LegalRAG: A Hybrid RAG System for Multilingual Legal Information Retrieval
topic Information Retrieval
Computation and Language
Machine Learning
url https://arxiv.org/abs/2504.16121