From Novice to Expert: Developing a Descriptive Competence Framework Guiding the Mastery of Large Language Models in Education
Saved in:
| Title: | From Novice to Expert: Developing a Descriptive Competence Framework Guiding the Mastery of Large Language Models in Education |
|---|---|
| Language: | English |
| Authors: | XiaoShu Xu (ORCID |
| Source: | Asia-Pacific Journal of Teacher Education. 2026 54(3):308-329. |
| Availability: | Taylor & Francis. Available from: Taylor & Francis, Ltd. 530 Walnut Street Suite 850, Philadelphia, PA 19106. Tel: 800-354-1420; Tel: 215-625-8900; Fax: 215-207-0050; Web site: http://www.tandf.co.uk/journals |
| Peer Reviewed: | Y |
| Page Count: | 22 |
| Publication Date: | 2026 |
| Document Type: | Journal Articles Reports - Research |
| Descriptors: | Novices, Expertise, Artificial Intelligence, Natural Language Processing, Technology Integration, Competence, Educational Technology, Mastery Learning, Learning Trajectories |
| DOI: | 10.1080/1359866X.2026.2675952 |
| ISSN: | 1359-866X 1469-2945 |
| Abstract: | This study introduces and validates the LLMs Expert User Competence Framework, a model for developing expertise in the educational use of Large Language Models (LLMs). Grounded in the Knowledge, Skills, and Attitudes (KSA) model, the framework outlines five progressive levels -- Novice, Beginner, Competent, Proficient, and Expert -- capturing the trajectory of user development. A multi-phase validation process included expert panel review (n = 8), pilot testing (n = 194), and a main survey (n = 502). Experts' qualitative and quantitative input led to key refinements, such as the inclusion of real-world applications, ethical considerations, and continuous professional learning. Quantitative results confirmed strong construct validity and internal consistency. Most participants identified as novices, particularly in operational skills, highlighting the need for structured training for teachers. Regression analyses showed that LLMs usage frequency and duration significantly predicted higher competence across all KSA domains. This study fills a critical gap in existing research by offering a comprehensive, scalable and descriptive framework to inform steps necessary for educators' responsible and progressive mastery of LLMs in educational contexts. |
| Abstractor: | As Provided |
| Entry Date: | 2026 |
| Accession Number: | EJ1508406 |
| Database: | ERIC |
| Abstract: | This study introduces and validates the LLMs Expert User Competence Framework, a model for developing expertise in the educational use of Large Language Models (LLMs). Grounded in the Knowledge, Skills, and Attitudes (KSA) model, the framework outlines five progressive levels -- Novice, Beginner, Competent, Proficient, and Expert -- capturing the trajectory of user development. A multi-phase validation process included expert panel review (n = 8), pilot testing (n = 194), and a main survey (n = 502). Experts' qualitative and quantitative input led to key refinements, such as the inclusion of real-world applications, ethical considerations, and continuous professional learning. Quantitative results confirmed strong construct validity and internal consistency. Most participants identified as novices, particularly in operational skills, highlighting the need for structured training for teachers. Regression analyses showed that LLMs usage frequency and duration significantly predicted higher competence across all KSA domains. This study fills a critical gap in existing research by offering a comprehensive, scalable and descriptive framework to inform steps necessary for educators' responsible and progressive mastery of LLMs in educational contexts. |
|---|---|
| ISSN: | 1359-866X 1469-2945 |
| DOI: | 10.1080/1359866X.2026.2675952 |
