cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Mukhibat
Contact Email
edukasiajurnal@gmail.com
Phone
+6289222090123
Journal Mail Official
edukasiajurnal@gmail.com
Editorial Address
Jalan Durian, Janggan, Poncol, Magetan,Indonesia
Location
Kab. magetan,
Jawa timur
INDONESIA
Edukasia: Jurnal Pendidikan dan Pembelajaran
Published by Lembaga Pendidikan Ma'arif NU Magetan
ISSN : 27211150     EISSN : 27211169     DOI : https://doi.org/10.5281/zenodo
Core Subject : Education,
Education Languange, Linguistic, Communication & Media Mathematics Other
Edukasia: Jurnal Pendidikan dan Pembelajaran has two versions, namely print and online, all of which are registered with the ISSN established by the Indonesian Institute of Sciences (LIPI) e-ISSN 2721-1169 (online) and ISSN 2721-1150 (print). Edukasia: Jurnal Pendidikan dan Pembelajaran is a medium for publishing research results related to the thoughts and research of experts, scientists, practitioners and reviewers in the field of education and learning
Arjuna Subject : Ilmu Sosial - Pendidikan
Articles 1,822 Documents
 179   180   181   182   183 
Learning Style Tendencies of Early Adult Community Education Students Across Cohorts Muhammad Irfan Hilmi; Jajat Sudrajat Ardiwinata; Deditiani Tri Indrianti; Sucianingsih Sucianingsih; Lutfi Ariefianto
EDUKASIA Jurnal Pendidikan dan Pembelajaran Vol. 7 No. 1 (2026)
Publisher : LP. Ma'arif Janggan Magetan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62775/edukasia.v7i1.2139

Abstract

This study examines learning style tendencies among early adult Community Education students and compares their distribution across three cohorts. It responds to limited evidence on Kolb-informed experiential learning tendencies in community education, especially when such data are used for program-level pedagogical reflection rather than psychological labeling. A quantitative cross-sectional descriptive-comparative survey was conducted with total sampling of complete and valid responses from active students in the 2022, 2023, and 2024 cohorts (N = 210). An 18-item practical inventory, conceptually mapped to Kolb's experiential learning dimensions, classified tendencies into diverging, assimilating, accommodating, and converging. Data were analyzed using frequency distribution, cross-tabulation, chi-square test, and Cramer's V. Results showed that diverging was the most common tendency (34.8%), followed by assimilating (33.8%), accommodating (19.5%), and converging (11.9%). Cross-cohort differences were not statistically significant (χ²(6, N = 210) = 4.60, p = .596, V = .10). The findings indicate a stable reflective profile and support multimodal experiential pedagogy for classroom learning and community lab-site practice.
Mitigating Hallucinations in Large Language Models via Retrieval Augmented Generation: A Systematic Review of n8n-Based Implementations I Ketut Widhi Adnyana; Rosalin Theophilia Tayane; Fahmi Fahmi; Freddy Wicaksono; Bagja Nugraha; Enjang Yusup Ali
EDUKASIA Jurnal Pendidikan dan Pembelajaran Vol. 7 No. 1 (2026)
Publisher : LP. Ma'arif Janggan Magetan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62775/edukasia.v7i1.2141

Abstract

This study systematically examines hallucination phenomena in Large Language Models (LLMs), focusing on their characteristics, causal factors, and mitigation strategies through Retrieval-Augmented Generation (RAG) and low-code orchestration platforms such as n8n. Using a Systematic Literature Review (SLR) approach based on PRISMA 2020 guidelines, this study analysed 40 peer-reviewed articles published between 2020 and 2025 from major scientific databases. The findings reveal that hallucinations are multidimensional, consisting of factual, semantic, and contextual hallucinations influenced by static training data, probabilistic token prediction, prompt ambiguity, and insufficient validation mechanisms. The review further demonstrates that RAG significantly improves factual accuracy by integrating external retrieval systems with LLM generation processes. Recent innovations such as Hybrid Retrieval and GraphRAG enhance contextual relevance and knowledge representation. A major finding of this study is the identification of “Conflict of Information” between external retrieved data and internal LLM knowledge in automated RAG pipelines. Furthermore, this study proposes a novel conceptual framework and taxonomy for hallucination mitigation in low-code AI environments, integrating retrieval, validation, conflict resolution, and workflow orchestration mechanisms. These findings contribute to the development of more reliable, transparent, and scalable AI systems.  

Page 183 of 183 | Total Record : 1822

 179   180   181   182   183 

Filter by Year

2020 2026


Reset
Filter By Issues
All Issue Vol. 7 No. 1 (2026) Vol. 6 No. 2 (2025): Edukasia: Jurnal Pendidikan dan Pembelajaran Vol. 6 No. 1 (2025): Edukasia: Jurnal Pendidikan dan Pembelajaran Vol. 5 No. 2 (2024): Edukasia: Jurnal Pendidikan dan Pembelajaran Vol. 5 No. 1 (2024): Edukasia: Jurnal Pendidikan dan Pembelajaran Vol. 4 No. 2 (2023): Edukasia: Jurnal Pendidikan dan Pembelajaran Vol. 4 No. 1 (2023): Edukasia: Jurnal Pendidikan dan Pembelajaran Vol. 3 No. 3 (2022): Edukasia: Jurnal Pendidikan dan Pembelajaran Vol. 3 No. 2 (2022): Edukasia: Jurnal Pendidikan dan Pembelajaran Vol. 3 No. 1 (2022): Edukasia: Jurnal Pendidikan dan Pembelajaran Vol. 2 No. 2 (2021): Edukasia: Jurnal Pendidikan dan Pembelajaran Vol. 2 No. 1 (2021): Edukasia: Jurnal Pendidikan dan Pembelajaran Vol. 1 No. 2 (2020): EDUKASIA: Jurnal Pendidikan dan Pembelajaran Vol. 1 No. 1 (2020): EDUKASIA: Jurnal Pendidikan dan Pembelajaran More Issue