Sistem Otomatisasi Ringkasan Literatur Berbahasa Indonesia Menggunakan Metode Retrieval-Augmented Generation (RAG) Dan Model IndoT5
DOI:
https://doi.org/10.29407/noe.v9i01.26866Keywords:
IndoT5, Literatur Akademik, Otomatisasi Ringkasan, Text SummarizationAbstract
Peningkatan jumlah publikasi ilmiah di Indonesia menimbulkan tantangan dalam menyaring dan memahami literatur secara efisien. Proses kajian literatur manual memerlukan waktu yang panjang, rentan terhadap bias kognitif, dan sulit mengikuti perkembangan riset terkini. Untuk mengatasi permasalahan ini, penelitian ini mengembangkan sistem otomatisasi ringkasan literatur yang mengintegrasikan Retrieval-Augmented Generation (RAG) dengan model IndoT5 dan pendekatan struktur IMRAD (Introduction, Methods, Results, and Discussion). Sistem menggabungkan proses peringkasan menggunakan IndoT5, indexing berbasis FAISS, serta embedding IndoBERT untuk pencarian dokumen yang relevan secara semantik. Evaluasi sistem menggunakan metrik BERTScore menunjukkan kualitas ringkasan dengan skor precision 0.828, recall 0.881, dan F1-score 0.854. Penilaian menggunakan LLM-as-a-Judge dengan model LLaMA-3-70B menghasilkan skor rata-rata 4.78 dari skala 5 untuk aspek relevansi, kebenaran, dan kelengkapan respons. Hasil penelitian membuktikan bahwa sistem mampu menghasilkan ringkasan yang informatif dan kontekstual, serta mempercepat proses kajian literatur berbahasa Indonesia secara signifikan.
Downloads
References
Cahyawijaya, S., Winata, G. I., Wilie, B., Vincentio, K., Li, X., Kuncoro, A., Ruder, S., Lim, Z. Y., Bahar, S., Khodra, M. L., Purwarianti, A., & Fung, P. (2021). IndoNLG: Benchmark and Resources for Evaluating Indonesian Natural Language Generation. http://arxiv.org/abs/2104.08200
Cheng, M., Luo, Y., Ouyang, J., Liu, Q., Liu, H., Li, L., Yu, S., Zhang, B., Cao, J., Ma, J., Wang, D., & Chen, E. (2025). A Survey on Knowledge-Oriented Retrieval-Augmented Generation. http://arxiv.org/abs/2503.10677
Gu, J., Jiang, X., Shi, Z., Tan, H., Zhai, X., Xu, C., Li, W., Shen, Y., Ma, S., Liu, H., Wang, S., Zhang, K., Wang, Y., Gao, W., Ni, L., & Guo, J. (2024). A Survey on LLM-as-a-Judge. http://arxiv.org/abs/2411.15594
Gupta, S., & Ranjan, R. (2024). A Comprehensive Survey of Retrieval-Augmented Generation (RAG): Evolution, Current Landscape and Future Directions.
Hahsler, M. (2023). ARULESPY: Exploring Association Rules and Frequent Itemsets in Python. http://arxiv.org/abs/2305.15263
Handoyo, S., Prastiti, P. I. D., & Stiaji, I. R. (2024). Bibliometric analysis of publications trends in Indonesian research institutions: A comparison of pre-integration (2015–2021) and post-integration (2022–2023) periods. European Science Editing, 50. https://doi.org/10.3897/ese.2024.e118015
Jaber, E. A., & Gérard, L.-A. (2025). Signature volatility models: pricing and hedging with Fourier. https://doi.org/10.1137/24M1636952
Li, D., Jiang, B., Huang, L., Beigi, A., Zhao, C., Tan, Z., Bhattacharjee, A., Jiang, Y., Chen, C., Wu, T., Shu, K., Cheng, L., & Liu, H. (2024). From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge. http://arxiv.org/abs/2411.16594
Muhammad, T., Rahardiansyah, R., Setya Perdana, R., & Fatyanosa, T. N. (2025). Analisis Teknik Embedding Model NV-Embed pada Large Language Models Berbasis Retrieval Augmented Generation (Vol. 9, Nomor 2). http://j-ptiik.ub.ac.id
Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2020). Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. Dalam Journal of Machine Learning Research (Vol. 21). http://jmlr.org/papers/v21/20-074.html.
Ridwan, M., Ulum, B., Muhammad, F., Indragiri, I., & Sulthan Thaha Saifuddin Jambi, U. (2021). Pentingnya Penerapan Literature Review pada Penelitian Ilmiah (The Importance Of Application Of Literature Review In Scientific Research). http://journal.fdi.or.id/index.php/jmas/article/view/356
Sakti Wiradinata, A., Viny, ), & Mawardi, C. (2024). Jurnal Ilmu Komputer dan Sistem Informasi Abstractive Text Summarization Berita Bahasa Indonesia Menggunakan Retrieval-Augmented Generation. https://www.cnbcindonesia.com/indeks
Shuliang Liu, Xinze Li, Zhenghao Liu, Yukun Yan, Cheng Yang, Zheni Zeng, Zhiyuan Liu, Maosong Sun, & Ge Yu. (2025). Judge as A Judge: Improving the Evaluation of Retrieval-Augmented Generation through the Judge-Consistency of Large Language Models.
Sollaci, L. B., & Pereira, M. G. (2004). The introduction, methods, results, and discussion (IMRAD) structure: a fifty-year survey. Dalam J Med Libr Assoc (Vol. 92, Nomor 3).
Vaswani, A., Brain, G., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., & Polosukhin, I. (2017). Attention Is All You Need.
Wilie, B., Vincentio, K., Winata, G. I., Cahyawijaya, S., Li, X., Lim, Z. Y., Soleman, S., Mahendra, R., Fung, P., Bahar, S., & Purwarianti, A. (2020). IndoNLU: Benchmark and Resources for Evaluating Indonesian Natural Language Understanding. http://arxiv.org/abs/2009.05387
Yani, M., Siti Khodijah, N., & Mustamiin, M. (2024). Aplikasi Peringkas Teks Bahasa Indonesia Menggunakan Model Text-to-Text Transfer Transformer (T5). https://doi.org/10.37817/ikraith-informatika.v9i2
Zhang, T., Kishore, V., Wu, F., Weinberger, K. Q., & Artzi, Y. (2019). BERTScore: Evaluating Text Generation with BERT. http://arxiv.org/abs/1904.09675
Zheng, L., Chiang, W.-L., Sheng, Y., Zhuang, S., Wu, Z., Zhuang, Y., Lin, Z., Li, Z., Li, D., Xing, E. P., Zhang, H., Gonzalez, J. E., & Stoica, I. (2023). Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena. http://arxiv.org/abs/2306.05685
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Aisyah Mufidah, Badie'ah
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Copyright on any article is retained by the author(s).
- The author grants the journal, right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work’s authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal’s published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
- The article and any associated published material is distributed under the Creative Commons Attribution-ShareAlike 4.0 International License
How to Cite
