Article Per Year (5 Year)
p-Index From 2021 - 2026
5.273
P-Index
This Author published in this journals
All Journal IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Sistemasi: Jurnal Sistem Informasi Jurnal ELTIKOM : Jurnal Teknik Elektro, Teknologi Informasi dan Komputer Sinkron : Jurnal dan Penelitian Teknik Informatika Jurnal Informatika Swabumi (Suara Wawasan Sukabumi) : Ilmu Komputer, Manajemen, dan Sosial Indonesian Journal on Software Engineering (IJSE) Perspektif : Jurnal Ekonomi dan Manajemen Universitas Bina Sarana Informatika Jurnal Teknik Komputer AMIK BSI Paradigma Jurnal Pilar Nusa Mandiri Jurnal Mitra Manajemen Jurnal Mantik Penusa JURNAL TEKNIK INFORMATIKA DAN SISTEM INFORMASI Al-Khidmah JURNAL TEKNOLOGI DAN OPEN SOURCE Jurnal Manajemen Informatika Jurnal Abdimas PHB : Jurnal Pengabdian Masyarakat Progresif Humanis Brainstorming EVOLUSI : Jurnal Sains dan Manajemen Jurnal Mantik JPKMI (Jurnal Pengabdian Kepada Masyarakat Indonesia) Journal of Applied Data Sciences Jurnal AbdiMas Nusa Mandiri Abditeknika - Jurnal Pengabdian Kepada Masyarakat Jurnal Abdimas Ekonomi dan Bisnis Jurnal Informatika Dan Tekonologi Komputer (JITEK) Jurnal Pengabdian Masyarakat Formosa (JPMF) Jurnal Ilmu Komputer dan Teknologi (IKOMTI) Abdi Teknoyasa Jurnal Aruna Mengabdi (ARMI) Journal of Accounting Information System Jurnal Informatika Dan Tekonologi Komputer
Hilda Rachmi
Universitas Bina Sarana Informatika
Aerospace Engineering Arts Humanities Automotive Engineering Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Environmental Science Languange, Linguistic, Communication & Media Mathematics Mechanical Engineering Physics Public Health Social Sciences Other

Published : 41 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 41 Documents
Search

 1   2   3   4   5 
A Hybrid TF-IDF and Knowledge Graph-Enhanced Retrieval-Augmented Generation Framework with Large Language Models for Domain-Aware Question Answering Lilyani Asri Utami; Hilda Rachmi; Syarif Hidayatulloh
Journal of Applied Data Sciences Vol 7, No 2: May 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i2.1136

Abstract

This study aims to develop a domain-aware legal Question-Answering (QA) system tailored for Indonesia’s Micro, Small, and Medium Enterprises (MSMEs) by proposing a hybrid Retrieval-Augmented Generation (RAG) framework that integrates Term Frequency–Inverse Document Frequency (TF-IDF), Knowledge Graph (KG), and Large Language Model (LLM) components. In this framework, TF-IDF contributes by performing lexical-level retrieval to identify the most relevant documents based on keyword weighting; the KG enriches this retrieval by providing semantic relationships among legal entities, enabling deeper contextual understanding; and the LLM generates coherent responses conditioned on both lexical and semantically grounded evidence. Together, these components work synergistically to strengthen factual grounding during retrieval and improve contextual reasoning during generation. Methodologically, the system processes a curated dataset of 1,400 legal question–answer pairs collected from national legal repositories, including legislation, government regulations, and MSME digitalization guidelines. The process includes text preprocessing, keyword extraction using TF-IDF, semantic enrichment through a KG that maps legal entities and their relationships, and answer generation via an LLM powered by the RAG pipeline. The system was evaluated using Precision, Recall, F1-Score, Bilingual Evaluation Understudy (BLEU), and Recall-Oriented Understudy for Gisting Evaluation (ROUGE) metrics, validated by five legal experts. Results show an accuracy improvement from 76.5% to 83.5% after integrating KG, with Precision of 0.853, Recall of 0.877, and F1-Score of 0.865. The generative evaluation yielded a BLEU score of 0.9276 and ROUGE-L of 0.9301, indicating strong linguistic and semantic alignment between system outputs and expert-authored references. The study concludes that this approach offers a practical foundation for building AI-based legal assistance tools and highlights future opportunities for expansion to other legal domains and multilingual RAG applications.
Co-Authors A.A. Ketut Agung Cahyawan W Abdul Hamid Ahmad Al Kaafi Ahmad Fauzi Ahmad MAULANA Amir Amir Arroyan Ilham Nafian Artika Surniandari Brilianto, Naufal Dini Nurlaela Fauzi Ahmad Muda Fransisco Fransisco Furi Indriyani Hani, Siti Haryani Helina Apriyani Hidayat, Nasrul Walid Ilham Ilham Imam Nawawi Imam Nawawi, Imam Kusmayanti Solecha Lila Dini Utami Lilyani Asri Utami, Lilyani Asri Lisda Widiastuti Muhamad Ikbal Septiana Muhammad Rizal Ahmad Naufal Brilianto Nurlaela, Siti Hani Nurtriani, Ririn Oky Irnawati Priyanti, Widi Intan Putie Maharani Putie Maharani Basa Rachmat Suryadithia Ria Septilinah Rietoni, Ahmad Temmy Risa Wati - AMIK BSI Tasikmalaya Risa Wati - AMIK BSI Tasikmalaya Rizaq Rifatulloh, Muhammad Sahrul Gunawan Silvy Nur Azizah Siti Ernawati Siti Hani Nurlaela Siti Nurwahyuni Siti Nurwahyuni Suparni Suparni Suparni Suparni Syarif Hidayatulloh Syarif Hidayatulloh Tanjung, Handra Putratama Wahyu Agung Nugroho Widi Intan Priyanti Yuwono, Roladina Tika