Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal International Journal of Advances in Data and Information Systems
Nyoman Gunantara
Faculty of Engineering, Universitas Udayana , Indonesia
Computer Science & IT Electrical & Electronics Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
An Optimization Framework for Retrieval Augmented Generation in Indonesian Educational Question Answering I Ketut Resika Arthana; Nyoman Gunantara; Made Sudarma; I Made Sukarsa
International Journal of Advances in Data and Information Systems Vol. 7 No. 2 (2026): August 2026 - International Journal of Advances in Data and Information Systems
Publisher : Indonesian Scientific Journal

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59395/ijadis.v7i2.1633

Abstract

The Retrieval-Augmented Generation (RAG) approach has been widely adopted to produce responses that are more closely aligned with a predefined knowledge context. However, many RAG implementations have not undergone systematic optimization of their retrieval and generation components, resulting in outputs that do not always correspond accurately to the reference context. This study developed a RAG optimization framework for Indonesian-language educational question answering using a Human-Computer Interaction learning corpus as a case study. In the retrieval stage, the study evaluated chunking strategies, multilingual embedding models, and the use of a reranker. Evaluation was conducted using Mean Reciprocal Rank (MRR), Normalized Discounted Cumulative Gain (nDCG@K), and Hit@K. In the generation stage, candidate Large Language Models (LLMs) were assessed using RAGAS metrics, namely Context Precision (CP), Context Recall (CR), Faithfulness (F), Answer Relevancy (AR), and Answer Correctness (AC). Experimental results showed that the GTE configuration with fixed-size chunking and a reranker yielded the best retrieval performance, achieving an MRR of 0.9082, nDCG@5 of 0.9215, and Hit@5 of 0.9655. In the generation stage, Gemma 4 E4B exhibited the most balanced answer quality. The resulting framework provides a procedure for selecting retrieval and generation settings for a given corpus.
Co-Authors I Ketut Resika Arthana I Made Sukarsa Made Sudarma