Melola Discovery

← Melola Discovery

Akses terbuka Jurnal SINTA 1

Reconstruction of the Phi-2 Method for Question-Answering Related to Diabetes Disease Using the MedAlpaca Dataset

Jambura Journal of Biomathematics (JJBM) · Vol. ume (2025) · hlm. 183–187

DOI
10.37905/jjbm.v6i3.30506
ISSN
2723-0317
Terbit
2025-09-01
Penerbit
Department of Mathematics, Universitas Negeri Gorontalo
Bahasa
eng
Lisensi
creativecommons.org/licenses/by-nc/4.0

Abstrak

This study focuses on the reconstruction of the Phi-2 method for text-based question-answering systems related to diabetes using the MedAlpaca dataset. The aim is to enhance the accuracy in diabetes question-answering applications. We leverage LoRA techniques to fine-tune the model, thereby improving its ability to handle complex medical queries. The integration of the MedAlpaca dataset, which contains a diverse range of medical questions and answers, provides a robust foundation for training and testing the model. The results reveal that fine-tuning with MedAlpaca significantly enhances the model’s performance, achieving higher accuracy compared to the base Phi-2 model, achieving a performance increase from 14.81% to 49.37% on MedMCQA, reaching 92.83% on PubMedQA, and 38.78% on MedQA. It also surpasses other leading models such as BioBERT (89.90%) and GatorTron (90.87%). The results highlight the effectiveness of incorporating domain-specific datasets like MedAlpaca to boost model performance. This advancement points to promising directions for future research, including expanding datasets and refining fine-tuning techniques to further improve automated medical question-answering systems.

Kata kunci

Jaringan kolaborasi para penulis

5 penulis · 6 tautan kepenulisan bersama

Arahkan kursor atau ketuk sebuah nama untuk menyorot rekan penulisnya. Klik dua kali untuk membuka halaman penulis.

  • University of Indonesia
  • Afiliasi tidak diketahui
  • Organisasi berbeda
  • Organisasi sama
  • Afiliasi tidak diketahui
  • Garis lebih tebal = lebih banyak artikel bersama · lingkaran lebih besar = lebih banyak artikel
Tampilkan sebagai tabel
Rekan penulisOrganisasiArtikel bersama
Titin SiswantiningUniversity of Indonesia1
Mohamad Irlin SunggawaUniversity of Indonesia1

Afiliasi berasal dari OpenAlex; metadata OAI-PMH jurnal tidak memuatnya. Penulis tanpa ID OpenAlex dicocokkan berdasarkan nama, sehingga dua orang bisa tergabung atau satu orang bisa terpisah.

Sumber metadata: OAI-PMH (metadata jurnal) http://ejurnal.ung.ac.id/index.php/JJBM/oai, pertama di-harvest 9 Nov 2026, terakhir terlihat 9 Nov 2026.
Metadata asli (oai_dc) 
<oai_dc:dc xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/  http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
	<dc:title xml:lang="en-US">Reconstruction of the Phi-2 Method for Question-Answering  Related to Diabetes Disease Using the MedAlpaca Dataset</dc:title>
	<dc:creator>Ridho, Muhammad</dc:creator>
	<dc:creator>Bustamam, Alhadi</dc:creator>
	<dc:creator>Adnan, Risman</dc:creator>
	<dc:subject xml:lang="en-US">Fine-Tuning; Phi-2; MedAlpaca; Question-Answering; Diabetes</dc:subject>
	<dc:description xml:lang="en-US">This  study  focuses on the reconstruction of the Phi-2  method  for text-based question-answering systems  related to diabetes  using the MedAlpaca dataset.   The  aim  is to enhance  the accuracy in  diabetes  question-answering applications.   We  leverage LoRA  techniques   to fine-tune  the model,  thereby  improving its  ability to handle complex medical queries.  The integration of the MedAlpaca dataset, which contains  a diverse range of medical questions  and answers,  provides a robust  foundation for training and testing the model.  The results  reveal  that fine-tuning  with   MedAlpaca  significantly  enhances   the  model’s   performance,  achieving  higher   accuracy compared to the base Phi-2  model,  achieving a performance increase  from  14.81% to 49.37% on MedMCQA, reaching  92.83%  on  PubMedQA, and  38.78%  on  MedQA. It  also  surpasses  other  leading  models   such  as BioBERT  (89.90%)   and   GatorTron  (90.87%).        The   results    highlight  the   effectiveness    of   incorporating domain-specific datasets  like  MedAlpaca to boost model  performance.  This  advancement points  to promising directions  for  future  research,   including  expanding datasets  and  refining fine-tuning techniques   to  further improve automated  medical question-answering systems.</dc:description>
	<dc:publisher xml:lang="en-US">Department of Mathematics, Universitas Negeri Gorontalo</dc:publisher>
	<dc:contributor xml:lang="en-US">This research was funded by Data Science Center, University of Indonesia and the Bioinformatics Laboratory</dc:contributor>
	<dc:date>2025-09-01</dc:date>
	<dc:type>info:eu-repo/semantics/article</dc:type>
	<dc:type>info:eu-repo/semantics/publishedVersion</dc:type>
	<dc:type xml:lang="en-US">Peer-reviewed Article</dc:type>
	<dc:format>application/pdf</dc:format>
	<dc:identifier>https://ejurnal.ung.ac.id/index.php/JJBM/article/view/30506</dc:identifier>
	<dc:identifier>10.37905/jjbm.v6i3.30506</dc:identifier>
	<dc:source xml:lang="en-US">Jambura Journal of Biomathematics (JJBM); Volume 6, Issue 3: September 2025; 183-187</dc:source>
	<dc:source>2723-0317</dc:source>
	<dc:source>10.37905/jjbm.v6i3</dc:source>
	<dc:language>eng</dc:language>
	<dc:relation>https://ejurnal.ung.ac.id/index.php/JJBM/article/view/30506/11644</dc:relation>
	<dc:rights xml:lang="en-US">Copyright (c) 2025 Muhammad Ridho, Alhadi Bustamam, Risman Adnan</dc:rights>
	<dc:rights xml:lang="en-US">https://creativecommons.org/licenses/by-nc/4.0</dc:rights>
</oai_dc:dc>