Scaffolding Middle-School Mathematics Curricula With Large Language Models
Abstract/Contents
- Abstract
- Despite well-designed curriculum materials, teachers often face challenges in their implementation due to diverse classroom needs. This paper investigates whether Large Language Models can support middle-school math teachers by helping create high-quality curriculum-aligned scaffolds that reflect expert teacher strategies. Through Cognitive Task Analysis with expert teachers, we identified the decision-making processes involved in scaffolding their curriculum. We incorporated these insights into three LLM approaches designed to create one specific instructional scaffold: warmup tasks that activate and refresh background knowledge. We evaluated the models against a novel dataset of benchmark examples collected from two curriculum experts and found that the LLM approaches perform comparably to, and often better than, the expert-created versions. This research highlights the potential of LLMs to support teachers in creating effective instructional scaffolds, offering significant implications for scalable instructional support and AI-driven educational tools.
Description
| Type of resource | text, still image |
|---|---|
| Publication date | May 30, 2024 |
Creators/Contributors
| Author | Malik, Rizwaan |
|---|
Subjects
| Subject | Curriculum Scaffolding |
|---|---|
| Subject | Human-computer interaction |
| Subject | Large Language Models |
| Genre | Text |
| Genre | Article |
| Genre | Poster |
| Genre | Posters |
Bibliographic information
Access conditions
- Use and reproduction
- User agrees that, where applicable, content will not be used to identify or to otherwise infringe the privacy or confidentiality rights of individuals. Content distributed via the Stanford Digital Repository may be subject to additional license and use restrictions applied by the depositor.
- License
- This work is licensed under a Creative Commons Attribution Non Commercial 4.0 International license (CC BY-NC).
Preferred citation
- Preferred citation
- Malik, R. (2024). Scaffolding Middle-School Mathematics Curricula With Large Language Models. Stanford Digital Repository. Available at https://purl.stanford.edu/gn930by3026. https://doi.org/10.25740/gn930by3026.
Collection
Education Data Science (EDS) Capstone Projects, Graduate School of Education
View other items in this collection in SearchWorksContact information
- Contact
- rizmalik@stanford.edu
Also listed in
Loading usage metrics...