Creating adaptive learning pathways for inquiry-based learning in school science using generative AI large language models
Bibliographic Data
| ID | 21589466 |
|---|---|
| Authors | Mafor Penn (0000-0001-6217-328X, University of Johannesburg, corresponding author), Umesh Ramnarain (0000-0003-4548-5913, University of Johannesburg) |
| Year | 2025 |
| Pages | 1-25 |
| Publication date | 2025-10-22 |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | International Journal of Science Education, Part B (JOURNAL) |
| Journal identifiers | ISSN: 2154-8455 • E-ISSN: 2154-8463 |
| Publisher | Informa UK Limited (PUBLISHER • GB) |
| DOI | 10.1080/09500693.2025.2574519 |
| OpenAlex | W4415441004 |
| Language | EN |
| Citations received | 1 |
| References cited | 36 |
This article explores the potential of generative artificial intelligence (GAI) tools to create adaptive learning pathways for inquiry-based learning (IBL) science instruction. The research compares tailored pathways from ChatGPT 4.0 and Llama 3.1 for differentiated inquiry instruction in science subjects. A qualitative approach was employed using a case study design to provide thick descriptions of Pathways from ChatGPT 4.0 and Llama3.1in supporting teachers to cater to personalised IBL instruction. Five science teachers were purposefully selected to generate and implement adaptive learning pathways for IBL instruction. Content analysis of GAI-generated pathways and teacher semi-structured interviews revealed insights into the performance of the GAI models and the usefulness of the pathways in teaching inquiry lessons. The findings revealed that LLM-based GAI engines could be used to address the individual learning needs of students in IBL science classrooms. Adaptive learning pathways showed great potential in differentiating instruction. ChatGPT 4.0 was seen to be more robust when compared with Llama 3.1. Challenges observed included difficulty keeping track of differentiated assessments, time management, ethical concerns and AI biases. These findings have implications for exploiting GAI tools when crafting IBL instruction. Some recommendations for teacher practice and research in developing adaptive learning pathways are also discussed
Adaptive Learning · Generative grammar · Generative model · Language acquisition · Learning Sciences · Science education · Science learning · Innovative Teaching and Learning Methods · Intelligent Tutoring Systems and Adaptive Learning · Online Learning and Analytics
Examining Science Education in ChatGPT
Scaffolding and Achievement in Problem-Based and Inquiry Learning
Application and theory gaps during the rise of Artificial Intelligence in Education
A Systematic Review of Research on Personalized Learning
Inquiry‐based science instruction—what is it and does it matter? Results from a research synthesis years 1984 to 2002
Artificial Intelligence education for young children
Meta-Analysis of Inquiry-Based Learning
The Measurement of Observer Agreement for Categorical Data
Adaptive Learning Using Artificial Intelligence in e-Learning
Appraising research on personalized learning
The synergy of generative AI and inquiry-based learning
The impact of artificial intelligence on scientific practices
Patterns of inquiry-based science instruction and student science achievement in Pisa 2015
International collaborative follow-up investigation of graduating high school students’ understandings of the nature of scientific inquiry
Informing research on generative artificial intelligence from a language and literacy perspective
Applying structural equation modeling to examine the role of teacher beliefs and practices in differentiated instruction in physical education
AI and formative assessment
Deconflating the ZPD and instructional scaffolding
A Coefficient of Agreement for Nominal Scales
Game-based collaborative scientific inquiry learning using realistic context and inquiry process-based multidimensional scaffolding
| Citations per year | 1 |
|---|---|
| Citation span | 2026 - 2026 (1) |
| Highly cited | No |