JTT (Jurnal Teknologi Terpadu)
Vol 14 No 2 (2026): JTT (Jurnal Teknologi Terpadu)

Pengembangan Sistem Tanya Jawab Penyakit Pernapasan Menggunakan Model Phi-4 dengan Pendekatan Retrieval-Augmented Generation

Salsabila Widya (Teknologi Informasi, Universitas Islam Negeri Ar-Raniry)
Hendri Ahmadian (Teknologi Informasi, Universitas Islam Negeri Ar-Raniry)
Nurrizqa (Teknologi Informasi, Universitas Islam Negeri Ar-Raniry)



Article Info

Publish Date
27 Oct 2026

Abstract

Large Language Model (LLM)-based question answering systems are capable of generating relevant responses; however, they still have the potential to produce information that is inconsistent with the underlying knowledge source. The Retrieval-Augmented Generation (RAG) approach addresses this limitation by retrieving relevant context before generating responses. This study aims to implement the Phi-4 model with the RAG approach for a respiratory disease question answering system and to evaluate the effect of the fine-tuning process on system performance. Fine-tuning was performed using the Low-Rank Adaptation (LoRA) method, while the RAG implementation employed the BAAI/bge-m3 embedding model and the ChromaDB vector database. The evaluation was conducted using the RAGAS framework with the Context Precision, Context Recall, Faithfulness, and Answer Relevancy metrics on 50 question-answer pairs, and the performance of the fine-tuned Phi-4 model was compared with that of the base Phi-4 model. The results show that the fine-tuned Phi-4 model achieved Context Precision, Context Recall, Faithfulness, and Answer Relevancy scores of 1.0000, 1.0000, 0.9855, and 0.6874, respectively. Compared with the base model, the fine-tuning process improved the Faithfulness and Answer Relevancy scores by 0.0776 and 0.0791, respectively, while the Context Precision and Context Recall scores remained at 1.0000. These results indicate that the fine-tuning process improves answer quality without affecting retrieval performance.

Copyrights © 2026






Journal Info

Abbrev

jtt

Publisher

Subject

Civil Engineering, Building, Construction & Architecture Control & Systems Engineering Materials Science & Nanotechnology Mechanical Engineering

Description

JTT (Jurnal Teknologi Terpadu) dengan ISSN 2477-5177 (media online) dan 2338-6649 (media cetak), adalah jurnal ilmiah yang mempublikasikan hasil penelitian dibidang inovasi teknologi terapan dengan cakupan: Teknik Mesin, Teknik Elektro, Teknik Sipil, dan Teknik ...