Yustika Heti Handal
Universitas Esa Unggul

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

Analisis Perbandingan Zero-Shot dan Fine-Tuning pada LLM Untuk Automated Essay Scoring Alexandria Felicia Seanne; Husnul Hadah; Yustika Heti Handal; Britney Levina Sukma; Budi Tjahyono
Jurnal Riset dan Aplikasi Mahasiswa Informatika (JRAMI) Vol. 7 No. 03 (2026): Jurnal Riset dan Aplikasi Mahasiswa Informatika (JRAMI)
Publisher : Program Studi Teknik Informatika, FTIK, Universitas Indraprasta PGRI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30998/jrami.v7i03.1452

Abstract

Automated Essay Scoring (AES) using Large Language Models (LLMs) is rapidly evolving, yet there remains a lack of studies comparing Zero-shot prompting and Fine-tuning approaches on open-weight LLM models. This study analyzes the comparison of these two approaches on the Qwen 2.5-1.5B-Instruct model using the ASAP-AES 2.0 dataset. The Zero-shot approach employs Role Prompting and Chain-of-Thought (CoT) techniques, while Fine-tuning uses Parameter-Efficient Fine-tuning (PEFT/LoRA). Evaluation was conducted using the Quadratic Weighted Kappa (QWK) and Root Mean Square Error (RMSE) metrics. The results show that the Zero-shot approach yields a QWK of 0.0069 with an extreme central tendency bias, while Fine-tuning yields a QWK of 0.3247 (fair agreement). These findings confirm that adapting a Fine-tuning approach is one way to produce a sufficiently accurate automatic essay grading system on small-scale open-weight models
Tinjauan Literatur Sistematis: Adopsi Hyperautomation dalam Pemrosesan Invoice dan Keuangan Berbasis Robotic Process Automation (RPA) Husnul Hadah; Yustika Heti Handal; Alexandria Felicia Seanne; Britney Levina Sukma; Budi Tjahyono
Jurnal Riset dan Aplikasi Mahasiswa Informatika (JRAMI) Vol. 7 No. 04 (2026): Jurnal Riset dan Aplikasi Mahasiswa Informatika (JRAMI)
Publisher : Program Studi Teknik Informatika, FTIK, Universitas Indraprasta PGRI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30998/jrami.v7i04.1450

Abstract

Digital transformation in financial systems has encouraged companies to implement automation to improve the speed, effectiveness, accuracy, and efficiency of business processes, particularly in financial and invoice management. However, manual processes still often cause delays and data entry errors. This study aims to analyze the implementation of end-to-end hyperautomation integrating Robotic Process Automation (RPA), Artificial Intelligence (AI), Document Intelligence, and other supporting technologies in financial and invoice automation processes, while identifying research gaps in its implementation. This study employs a Systematic Literature Review (SLR) method using the PRISMA approach on peer-reviewed empirical articles published between 2021 and 2026. Out of 45 identified articles, 20 were selected for further analysis. The findings reveal that studies on end-to-end hyperautomation implementation in financial and invoice processes remain very limited, while most existing studies still focus on partial automation technologies, such as RPA, OCR, or AI separately. These findings highlight a significant research gap in the comprehensive integration of hyperautomation, providing opportunities for developing more integrated automation models to enhance efficiency, effectiveness, and minimize human error in business processes.