Implementasi pelatihan AI multimodal berbasis human-in-the-loop untuk penilaian melalui bank kasus lintas bidang di SMK Negeri 1 Bantul
DOI:
https://doi.org/10.59025/px7a5s45Keywords:
AI multimodal; bank kasus; human-in-the-loop; penilaian; pelatihan guruAbstract
Pemanfaatan kecerdasan buatan (AI) generatif dan multimodal membuka peluang untuk mendukung penilaian respons peserta didik. Namun, penggunaannya tetap memerlukan verifikasi manusia karena kesalahan dapat terjadi sejak pembacaan dokumen hingga pemberian skor dan umpan balik. Kegiatan pengabdian ini bertujuan mengimplementasikan pelatihan AI multimodal berbasis human-in-the-loop untuk mendukung penilaian dan mengembangkan bank kasus lintas bidang sebagai perangkat pelatihan. Kegiatan dilaksanakan pada 14–17 Juli 2026 di SMK Negeri 1 Bantul dan diikuti oleh 20 guru lintas bidang. Pelatihan mencakup pengenalan AI generatif dan multimodal, demonstrasi ChatGPT, Gemini, dan DeepSeek, latihan berbasis bank kasus, serta verifikasi keluaran AI. Bank kasus terdiri atas 30 butir dari Fisika, Kalkulus, barisan dan deret geometri, serta Sejarah Indonesia. Evaluasi tindak lanjut menggunakan 12 pernyataan skala Likert. Hasil evaluasi menunjukkan rerata penilaian sebesar 4,36 dari skala 5 dan 90,0% respons berada pada kategori setuju atau sangat setuju. Analisis artefak mengidentifikasi enam area yang memerlukan verifikasi manusia, mulai dari penyiapan dokumen hingga keputusan akhir. Hasil kegiatan menunjukkan bahwa AI dapat digunakan sebagai alat bantu penilaian, sedangkan keputusan akhir tetap berada pada guru.
References
Barrot, J. S. (2026). Generative artificial intelligence for automated essay scoring: Exploring teacher agency through an ecological perspective. Assessing Writing, 67, 100990. https://doi.org/10.1016/j.asw.2025.100990
Bowen, G. A. (2009). Document analysis as a qualitative research method. Qualitative Research Journal, 9(2), 27–40. https://doi.org/10.3316/QRJ0902027
Cui, Y., Meng, Y., & Tang, L. (2025). Reconsidering teacher assessment literacy in GenAI-enhanced environments: A scoping review. Teaching and Teacher Education, 165, 105163. https://doi.org/10.1016/j.tate.2025.105163
Ding, A.-C. E., Shi, L., Yang, H., & Choi, I. (2024). Enhancing teacher AI literacy and integration through different types of cases in teacher professional development. Computers and Education Open, 6, 100178. https://doi.org/10.1016/j.caeo.2024.100178
Elo, S., Kääriäinen, M., Kanste, O., Pölkki, T., Utriainen, K., & Kyngäs, H. (2014). Qualitative content analysis: A focus on trustworthiness. SAGE Open, 4(1). https://doi.org/10.1177/2158244014522633
Gülle, T., Aksu Dunya, B., & Demir, M. C. (2026). Evaluating the effectiveness of ChatGPT in rubric development. Assessing Writing, 69, 101067. https://doi.org/10.1016/j.asw.2026.101067
Holmes, W., Porayska-Pomsta, K., Holstein, K., Sutherland, E., Baker, T., Buckingham Shum, S., Santos, O. C., Rodrigo, M. T., Cukurova, M., Bittencourt, I. I., & Koedinger, K. R. (2022). Ethics of AI in education: Towards a community-wide framework. International Journal of Artificial Intelligence in Education, 32, 504–526. https://doi.org/10.1007/s40593-021-00239-1
Hsieh, H.-F., & Shannon, S. E. (2005). Three approaches to qualitative content analysis. Qualitative Health Research, 15(9), 1277–1288. https://doi.org/10.1177/1049732305276687
Indaryanti, Sari, N., Sofia, & Lesmana, H. (2025). Asesmen formatif digital: Pendampingan guru MGMP Matematika SMP OKU Timur memanfaatkan artificial intelligence. Abdi: Jurnal Pengabdian dan Pemberdayaan Masyarakat, 7(2), 643–653. https://doi.org/10.24036/abdi.v7i2.1486
Kaldaras, L., Yoshida, N. R., & Haudek, K. C. (2022). Rubric development for AI-enabled scoring of three-dimensional constructed-response assessment aligned to NGSS learning progression. Frontiers in Education, 7, 983055. https://doi.org/10.3389/feduc.2022.983055
Lee, G.-G., Latif, E., Wu, X., Liu, N., & Zhai, X. (2024). Applying large language models and chain-of-thought for automatic scoring. Computers and Education: Artificial Intelligence, 6, 100213. https://doi.org/10.1016/j.caeai.2024.100213
Memarian, B., & Doleck, T. (2024). Human-in-the-loop in artificial intelligence in education: A review and entity-relationship (ER) analysis. Computers in Human Behavior: Artificial Humans, 2(1), 100053. https://doi.org/10.1016/j.chbah.2024.100053
Ng, D. T. K., Leung, J. K. L., Chu, S. K. W., & Qiao, M. S. (2021). Conceptualizing AI literacy: An exploratory review. Computers and Education: Artificial Intelligence, 2, 100041. https://doi.org/10.1016/j.caeai.2021.100041
Nguyen, A., Ngo, H. N., Hong, Y., Dang, B., & Nguyen, B.-P. T. (2023). Ethical principles for artificial intelligence in education. Education and Information Technologies, 28, 4221–4241. https://doi.org/10.1007/s10639-022-11316-w
Puspandari, D., Prasetiyowati, S. S., & Sibaroni, Y. (2025). Pelatihan penggunaan AI untuk peningkatan kompetensi guru-guru dalam menyiapkan proses pembelajaran. Dinamisia: Jurnal Pengabdian Kepada Masyarakat, 9(1), 34–41. https://doi.org/10.31849/dinamisia.v9i1.20929
Quah, B., Zheng, L., Sng, T. J. H., Yong, C. W., & Islam, I. (2024). Reliability of ChatGPT in automated essay scoring for dental undergraduate examinations. BMC Medical Education, 24, 962. https://doi.org/10.1186/s12909-024-05881-6
Saputra, I., Hayatunnufus, Dewi, S. M., Reflianto, Putri, E. Y., & Mahniza, M. (2024). Pelatihan digitalisasi sumber belajar, asesmen, dan evaluasi pembelajaran berbasis ChatGPT bagi guru SMPN 9 Payakumbuh. SELAPARANG: Jurnal Pengabdian Masyarakat Berkemajuan, 8(4), 3237–3248. https://doi.org/10.31764/jpmb.v8i4.26825
Tan, X., Cheng, G., & Ling, M. H. (2025). Artificial intelligence in teaching and teacher professional development: A systematic review. Computers and Education: Artificial Intelligence, 8, 100355. https://doi.org/10.1016/j.caeai.2024.100355
Tri Aji, P., Nasuha, A., Irmawati, D., Sofyan, M. A. H., & Musaddid, A. T. (2024). Teacher competence in the use of ChatGPT for developing learning media in vocational high schools. International Journal of Community Service Learning, 8(4), 407–414. https://doi.org/10.23887/ijcsl.v8i4.85397
Zhu, H., Li, T., He, P., & Zhou, J. (2025). Enhancing automated grading in science education through LLM-driven causal reasoning and multimodal analysis. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence (pp. 10352–10360). https://doi.org/10.24963/ijcai.2025/1150
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Handaru Jati, Yuniar Indrihapsari, Susilo Romadhon, Pradana Setialana, Rheisan Firnandatama Rizky Satria
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
How to Cite
This work is licensed under a 