EUVIMEDEUVIMED entdecken
Crossref

Improving FAQ Retrieval for Academic Regulations Using Semantic Embeddings and LLM Question Augmentation

Fajri Profesio Putra, I Gusti Agung Putu Mahendra, Agus Tedyyana, Muhammad Noor

Jurnal Testing dan Implementasi Sistem Informasi · 27.05.2026 · 4 (1) · 1-19

DOI: 10.55583/jtisi.v4i1.2176 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Jurnal Testing dan Implementasi Sistem Informasi, online erschienen am 27.05.2026. Verfasst von Fajri Profesio Putra und 3 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Academic regulations in higher education are often documented in lengthy and formal handbooks, making it difficult for students to find relevant information using everyday language. This study developed a semantic FAQ retrieval system for academic regulations using IndoSBERT and question augmentation. The FAQ corpus was constructed from official academic and internship documents, resulting in 92 FAQ entries across 33 topical categories. Seed questions were generated from category–keyword pairs and expanded using simple rule-based augmentation and FLAN-T5-based paraphrasing. The dataset was evaluated using an 80:10:10 train–validation–test split. IndoSBERT was fine-tuned with Multiple Negatives Ranking Loss under three configurations: baseline, baseline with simple augmentation, and baseline with simple plus LLM-based augmentation. Retrieval performance was measured using Recall@1, Recall@3, Recall@5, and Mean Reciprocal Rank. The best result was achieved by the simple plus LLM augmentation configuration, with Recall@1 of 0.7848, Recall@5 of 0.8987, and MRR of 0.8396. These findings show that LLM-based question augmentation improves semantic retrieval robustness while keeping answers grounded in curated academic regulations.

Zitieren

APA

Putra, F. P., Mahendra, I. G. A. P., Tedyyana, A., & Noor, M. (2026). Improving FAQ Retrieval for Academic Regulations Using Semantic Embeddings and LLM Question Augmentation. Jurnal Testing dan Implementasi Sistem Informasi, 4(1), 1-19. https://doi.org/10.55583/jtisi.v4i1.2176

Vancouver

Putra FP, Mahendra IGAP, Tedyyana A, Noor M. Improving FAQ Retrieval for Academic Regulations Using Semantic Embeddings and LLM Question Augmentation. Jurnal Testing dan Implementasi Sistem Informasi. 2026;4(1):1-19. doi:10.55583/jtisi.v4i1.2176

BibTeX
@article{Putra2026,
  author = {Putra, Fajri Profesio and Mahendra, I Gusti Agung Putu and Tedyyana, Agus and Noor, Muhammad},
  title = {Improving FAQ Retrieval for Academic Regulations Using Semantic Embeddings and LLM Question Augmentation},
  journal = {Jurnal Testing dan Implementasi Sistem Informasi},
  year = {2026},
  volume = {4},
  number = {1},
  pages = {1--19},
  doi = {10.55583/jtisi.v4i1.2176}
}
Kostenlos starten →