A Locally Grounded Retrieval-Augmented LLM-Based Chatbot for Bilingual Stunting Prevention Consultation among Health Cadres in Indonesia

Tanwir Tanwir; Khasnur  Hidjah; Dyah  Susilowati; Anthony  Anggrawan; Neny  Sulistianingsih

doi:10.52436/1.jutif.2026.7.2.5459

Authors

Tanwir Department of Computer Science, Faculty of Engineering, Universitas Bumigora, Indonesia
Khasnur Hidjah Department of Computer Science, Faculty of Engineering, Universitas Bumigora, Indonesia
Dyah Susilowati Department of Information Technology Education, Faculty of Education, Universitas Bumigora, Indonesia
Anthony Anggrawan Department of Information Technology Education, Faculty of Education, Universitas Bumigora, Indonesia
Neny Sulistianingsih Department of Computer Science, Faculty of Engineering, Universitas Bumigora, Indonesia

DOI:

https://doi.org/10.52436/1.jutif.2026.7.2.5459

Keywords:

Bilingual Chatbot, Health Cadres, LLM-RAG, Rural Informatics, Stunting Prevention

Abstract

Stunting remains a major public health challenge in Indonesia, affecting 21.6% of children under five nationally and 18.34% in Nusa Tenggara Barat (NTB), which strains the capacity of health cadres to deliver timely and accurate nutrition education. This study aims to develop a consultation chatbot by integrating Large Language Models (LLMs) with Retrieval-Augmented Generation (RAG) to provide context-aware stunting prevention guidance. A total of 45 journal articles and 7 books were curated to construct 7,642 question–answer pairs using a RAG-based pipeline. Text preprocessing involved segmentation, embedding, and Byte Pair Encoding tokenization, followed by fine-tuning a LLaMA 3 model on an NVIDIA L4 GPU. Model performance was evaluated using ROUGE and BERTScore metrics, complemented by a small pilot usability assessment. The RAG-integrated model achieved a ROUGE-1 score of 81.03% and a BERTScore F1 of 93.48%, consistently outperforming baseline models. These findings demonstrate the potential of RAG-enhanced LLMs to support scalable and accessible health informatics solutions for empowering health cadres in resource-limited and rural settings.

Downloads

Download data is not yet available.

References

A. Waller, M. Lakhanpaul, S. Godfrey, and P. Parikh, “Multiple and complex links between babyWASH and stunting: an evidence synthesis,” Journal of Water, Sanitation and Hygiene for Development, vol. 10, no. 4, pp. 786–805, Dec. 2020, doi: 10.2166/washdev.2020.265.

L. Atamou, D. C. Rahmadiyah, H. Hassan, and A. Setiawan, “Analysis of the Determinants of Stunting among Children Aged below Five Years in Stunting Locus Villages in Indonesia,” Healthcare, vol. 11, no. 6, p. 810, Mar. 2023, doi: 10.3390/healthcare11060810.

A. Majid, M. Zahara, and A. Abdullah, “Science Midwifery Knowledge and skills in combating stunting in toddlers in Aceh Besar regency (a comparative study of BKKBN cadres with Integrated Service Post cadres),” Online, 2024. [Online]. Available: www.midwifery.iocspublisher.orgJournalhomepage:www.midwifery.iocspublisher.org

UNICEF, “Levels and Trends in Child Malnutrition,” UNICEF/WHO/World Bank Group Joint Child Malnutrition Estimates, 2023.

Kemkes, “Prevalensi Stunting di Indonesia Turun ke 21,6% dari 24,4%,” 2023.

H. S. Mediani, S. Hendrawati, T. Pahria, A. S. Mediawati, and M. Suryani, “Factors Affecting the Knowledge and Motivation of Health Cadres in Stunting Prevention Among Children in Indonesia,” J Multidiscip Healthc, vol. Volume 15, pp. 1069–1082, May 2022, doi: 10.2147/JMDH.S356736.

R. Eardley et al., “Explanation before Adoption: Supporting Informed Consent for Complex Machine Learning and IoT Health Platforms,” Proc ACM Hum Comput Interact, vol. 7, no. CSCW1, pp. 1–25, Apr. 2023, doi: 10.1145/3579482.

Q. Rachmah et al., “Peningkatan Pengetahuan Gizi Terkait Makanan Pendamping Asi (Mp-Asi) Melalui Edukasi Dan Hands-On-Activity Pada Kader Dan Non-Kader,” Media Gizi Indonesia, vol. 17, no. 1SP, pp. 47–52, Dec. 2022, doi: 10.20473/mgi.v17i1sp.47-52.

Dinas Kesehatan, “Jumlah Balita berdasarkan Status Gizi Kurang, Pendek dan Kurus di Nusa Tenggara Barat.” Accessed: Apr. 10, 2025. [Online]. Available: https://data.ntbprov.go.id/index.php/dataset/9d274132-1480-48ea-aacf-14426b63c7d6/show

S. Palutturi, A. Syam, A. Asnawi, and Hamzah, “Stunting in a political context: A systematic review,” Enferm Clin, vol. 30, pp. 95–98, Jun. 2020, doi: 10.1016/j.enfcli.2019.10.049.

T. Tanwir, K. Hidjah, and D. Susilowati, “Implementasi Konsultasi Stunting Balita Menggunakan Large Language Models (LLMs),” Reputasi: Jurnal Rekayasa Perangkat Lunak, vol. 6, no. 1, pp. 13–20, Jun. 2025, doi: 10.31294/reputasi.v6i1.8961.

A. Gangavarapu, “LLMs: A Promising New Tool for Improving Healthcare in Low-Resource Nations,” in 2023 IEEE Global Humanitarian Technology Conference (GHTC), IEEE, Oct. 2023, pp. 252–255. doi: 10.1109/GHTC56179.2023.10354650.

A. Goel et al., “LLMs Accelerate Annotation for Medical Information Extraction,” Dec. 2023, [Online]. Available: http://arxiv.org/abs/2312.02296

Y. Choi, C. Na, H. Kim, and J.-H. Lee, “READSUM: Retrieval-Augmented Adaptive Transformer for Source Code Summarization,” IEEE Access, vol. 11, pp. 51155–51165, 2023, doi: 10.1109/ACCESS.2023.3271992.

B. Hieronimus, M.-L. Lopez-Aguirre, M. Birringer, and M. Podszun, “GenAI in nutritional sciences (GAINS): A systematic review and reporting framework for future research,” Nutrition Research, vol. 143, pp. 66–77, Nov. 2025, doi: 10.1016/j.nutres.2025.09.011.

F. Zhao, Q. Li, M. Wang, and X. Xiong, “An AI Agent-Based System for Retrieving Compound Information in Traditional Chinese Medicine,” Information (Switzerland), vol. 16, no. 7, Jul. 2025, doi: 10.3390/info16070543.

H. Karim and D. Ariatmanto, “Methods for Development Mobile Stunting Application: A Systematic Literature Review,” Sinkron, vol. 9, no. 1, pp. 244–257, Jan. 2024, doi: 10.33395/sinkron.v9i1.13123.

R. Novianti Utami, S. L. Panduragan, and N. Nambiar, “Leveraging Mobile Applications for Stunting Prevention in Indonesia: A Scoping Review,” The Malaysian Journal of Nursing, vol. 16, no. 02, pp. 158–167, 2025, doi: 10.31674/mjn.2025.v16isupp2.018.

S. Miftahul Khoeriyah et al., “Digital Education as an Innovative Strategy for Stunting Prevention: A Literature Review,” Indonesian Journal of Global Health Research, vol. 7, Jul. 2025, doi: 10.37287/ijghr.v7i4.7035.

K. R. Darusman, T. Sundjaya, E. Wasito, B. Masita, and S. Fujianti, “Effectiveness of digital intervention for early stunting prevention in Indonesian children,” Bali Medical Journal, vol. 13, no. 3, pp. 1559–1565, Nov. 2024, doi: 10.15562/bmj.v13i3.5591.

I. K. Pangaribuan, F. A. M. Mendrofa, and G. Gunarmi, “Stunting Prevention Efforts Through Mentoring the Use of the SCATION (Stunting Care Application) for Mothers of Toddlers in the Medan City Community Health Center Work Area,” Open Access Health Scientific Journal, vol. 6, no. 2, pp. 336–341, Aug. 2025, doi: 10.55700/oahsj.v6i2.118.

I. Sutedja, L. Handayani, Maryuni, Hendry, and M. R. Faisal, “Analysis Implementation of Chatbots to Increase Knowledge of Stunting Prevention in Indonesian Society with Bibliometric,” in 2024 International Conference on Information Management and Technology (ICIMTech), IEEE, Aug. 2024, pp. 473–477. doi: 10.1109/ICIMTech63123.2024.10780895.

E. S. Nur Aulia, G. Jati, I. Wibowo, H. N. Muhammad, and E. Saepudin, “Chatbots Be Nutritionists: Exploring the Potential of AI-Powered to Improve Nutritional Counseling in Indonesia,” Jurnal Sosioteknologi, vol. 23, no. 3, pp. 324–335, Nov. 2024, doi: 10.5614/sostek.itbj.2024.23.3.2.

E. Sulistyorini, N. Ratnasari, F. Hayu Palupi, Lefiyana, and M. Ilham A, “Upaya Pencegahan Stunting melalui Penguatan Kapasitas Kader Posyandu dalam Tehnik Komunikasi Antar Pribadi (KAP) dan Pembuatan Media Konseling Berbasis Artificial Intelegence (AI),” PADMA, vol. 4, no. 2, pp. 455–465, Dec. 2024, doi: 10.56689/padma.v4i2.1462.

A. Salsabila, S. Wirawan, and A. Sitasari, “Telegram Chatbot as DASH Diet Education Media for Employees,” Window of Health : Jurnal Kesehatan, pp. 131–140, Apr. 2024, doi: 10.33096/woh.vi.1250.

S. H. Ali et al., “Rapid, Tailored Dietary and Health Education Through A Social Media Chatbot Microintervention: Development and Usability Study With Practical Recommendations,” JMIR Form Res, vol. 8, p. e52032, Dec. 2024, doi: 10.2196/52032.

P. Rajeshkumar, S. Kharche, P. Poojari, S. Utekar, S. Saini, and S. Bidwai, “DermAI: An Innovative AI-Driven Chatbot for Enhanced Dermatological Diagnosis and Patient Interaction,” Indonesian Journal of Electrical Engineering and Informatics (IJEEI), vol. 12, no. 4, Dec. 2024, doi: 10.52549/ijeei.v12i4.5806.

H. M. Alghamdi and A. Mostafa, “Towards Reliable Healthcare LLM Agents: A Case Study for Pilgrims during Hajj,” Information, vol. 15, no. 7, p. 371, Jun. 2024, doi: 10.3390/info15070371.

T. Luangaphirom, L. Jocknoi, C. Wunchum, K. Chokerungreang, and T. Siriborvornratanakul, “ThaiNutriChat: development of a Thai large language model-based chatbot for health food services,” Multimed Syst, vol. 30, no. 5, p. 298, Oct. 2024, doi: 10.1007/s00530-024-01495-6.

G. Soman, M. V. Judy, and A. M. Abou, “Human guided empathetic AI agent for mental health support leveraging reinforcement learning-enhanced retrieval-augmented generation,” Cogn Syst Res, vol. 90, p. 101337, Apr. 2025, doi: 10.1016/j.cogsys.2025.101337.

T. Lai et al., “Supporting the Demand on Mental Health Services with AI-Based Conversational Large Language Models (LLMs),” BioMedInformatics, vol. 4, no. 1, pp. 8–33, Mar. 2024, doi: 10.3390/biomedinformatics4010002.

T. Bano et al., “Utilizing Retrieval-Augmented Large Language Models for Pregnancy Nutrition Advice,” 2024, pp. 85–96. doi: 10.1007/978-3-031-66635-3_8.

S. Gilbert, J. N. Kather, and A. Hogan, “Augmented non-hallucinating large language models as medical information curators,” NPJ Digit Med, vol. 7, no. 1, p. 100, Apr. 2024, doi: 10.1038/s41746-024-01081-0.

J. Wang, E. Hanson, G. Li, Y. Papakonstantinou, H. Simhadri, and C. Xie, “Vector Databases: What’s Really New and What’s Next? (VLDB 2024 Panel),” Proceedings of the VLDB Endowment, vol. 17, no. 12, pp. 4505–4506, Aug. 2024, doi: 10.14778/3685800.3685911.

Aradhya KC and Divya TL, “Vector Databases,” Open Access Research Journal of Engineering and Technology, vol. 7, no. 1, pp. 096–104, Sep. 2024, doi: 10.53022/oarjet.2024.7.1.0043.

P. Lewis et al., “Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks,” May 2020, [Online]. Available: http://arxiv.org/abs/2005.11401

C. Munley, A. Jarmusch, and S. Chandrasekaran, “LLM4VV: Developing LLM-driven testsuite for compiler validation,” Future Generation Computer Systems, vol. 160, pp. 1–13, Nov. 2024, doi: 10.1016/j.future.2024.05.034.

C. Si et al., “Sub-Character Tokenization for Chinese Pretrained Language Models,” Trans Assoc Comput Linguist, vol. 11, pp. 469–487, May 2023, doi: 10.1162/tacl_a_00560.

C. Curto, D. Giordano, D. G. Indelicato, and V. Patatu, “Can a Llama Be a Watchdog? Exploring Llama 3 and Code Llama for Static Application Security Testing,” in 2024 IEEE International Conference on Cyber Security and Resilience (CSR), IEEE, Sep. 2024, pp. 395–400. doi: 10.1109/CSR61664.2024.10679444.

S. Kumar, A. Solanki, and N. Jhanjhi, “ROUGE-SS: A New ROUGE Variant for the Evaluation of Text Summarization,” Recent Advances in Computer Science and Communications, vol. 17, Jun. 2024, doi: 10.2174/0126662558304595240528111535.

F. V. P. Samosir, H. Toba, and M. Ayub, “BESKlus : BERT Extractive Summarization with K-Means Clustering in Scientific Paper,” Jurnal Teknik Informatika dan Sistem Informasi, vol. 8, no. 1, Apr. 2022, doi: 10.28932/jutisi.v8i1.4474.