eprintid: 72924
rev_number: 10
eprint_status: archive
userid: 12460
dir: disk0/00/07/29/24
datestamp: 2025-09-15 08:27:26
lastmod: 2025-09-15 08:27:26
status_changed: 2025-09-15 08:27:26
type: thesis
metadata_visibility: show
contact_email: muh.khabib@uin-suka.ac.id
creators_name: Muhammad Arif Rakhman Azizi, NIM.: 21106050042
title: RANCANG BANGUN VISUAL STUDIO CODE EXTENSION CODEVA UNTUK CODE GENERATOR JAVA SECARA OTOMATIS MENGGUNAKAN LARGE LANGUAGE MODELS (LLMs)
ispublished: pub
subjects: 005.12.
divisions: Informatika(S1)
full_text_status: restricted
keywords: Large Language Models, Fine Tuning, Ekstensi, Unsloth
note: Dr. Agung Fatwanto, S.Si., M.Kom.
abstract: The rapid advancement of technology has spurred a significant demand for
software, yet the Coding phase, particularly in a complex language like Java,
remains a time-consuming and error-prone process. To address this, a Visual
Studio Code Extension named CodeVa was developed to automatically generate
Java code using Large Language Models (LLMs).
Developed using the Agile Extreme Programming method ology, CodeVa
integrates a fine-tuned Open-source model, Qwen2.5 Instruct 7B. This model was
specifically trained for Java code generation using the Parameter-Efficient Finetuning
(PEFT) technique, Low-Rank Adaptation (LoRA), and the Unsloth
framework.
The fine-tuning process resulted in substantial improvements across various
performance metrics, including an increase in the CodeBLEU score from 0.3204 to
0.3521 and significant gains in ROUGE scores ROUGE-1 from 0.1736 to 0.3705,
ROUGE-2 from 0.0251 to 0.2278, and ROUGE-L from 0.0991 to 0.3252 and
Pass@10 using kulal version and chen version from 73.17% to 73.78%. Usability
testing of CodeVa yielded a System Usability Scale (SUS) score of 81.0,
categorizing it as "excellent" and "acceptable." This indicates that CodeVa is a
highly effective tool that can significantly enhance developer productivity by
facilitating faster and more efficient Java Coding .
date: 2025-08-14
date_type: published
pages: 123
institution: UIN SUNAN KALIJAGA YOGYAKARTA
department: FAKULTAS SAINS DAN TEKNOLOGI
thesis_type: skripsi
thesis_name: other
citation:   Muhammad Arif Rakhman Azizi, NIM.: 21106050042  (2025) RANCANG BANGUN VISUAL STUDIO CODE EXTENSION CODEVA UNTUK CODE GENERATOR JAVA SECARA OTOMATIS MENGGUNAKAN LARGE LANGUAGE MODELS (LLMs).  Skripsi thesis, UIN SUNAN KALIJAGA YOGYAKARTA.   
document_url: https://digilib.uin-suka.ac.id/id/eprint/72924/1/21106050042_BAB-I_IV-atau-V_DAFTAR-PUSTAKA.pdf
document_url: https://digilib.uin-suka.ac.id/id/eprint/72924/2/21106050042_BAB-II_sampai_SEBELUM-BAB-TERAKHIR.pdf