Evaluating an AI-powered Platform for Generating Instructional Materials on Mathematical Modelling of Direct Variation
Bibliographic record
Abstract
Mathematical modelling serves as the foundation for addressing real-world problems. In Hong Kong, the Education Bureau has promoted teacher awareness, yet a lack of instructional materials for conducting mathematical modelling activities remains. Therefore, we have developed an AI-powered platform to generate mathematical modelling problems and pedagogical recommendations to support teaching practices. To ensure a robust foundation for problem generation, our instruction input to the AI model (GPT-40) encompassed established design frameworks and principles. This study focused on the topic of direct variation within the secondary school mathematics curriculum. We tasked the AI tool with creating 20 sets of instructional materials for our evaluation. Furthermore, we engaged five well-trained in-service teachers to trial the platform and provide feedback for improvement. Our findings suggested that the AI-generated problems were generally relevant to real-world contexts. Our teacher participants further highlighted the clarity and comprehensiveness of the AI-generated teacher guides, which offered detailed pedagogical recommendations and suggested solutions. Most importantly, the instructional materials aligned with curriculum standards and catered to the ability levels of students in Hong Kong. However, the AI tool still requires human oversight. Specifically, the AI-generated units and values (e.g., the price of petrol) should be verified to ensure their accuracy and relevance to current real-world contexts. Our next steps involve refining the AI tool to address the identified issues and training it to generate instructional materials across a wider range of mathematics topics, thereby enhancing its overall effectiveness and applicability.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.011 | 0.053 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.004 |
| Open science | 0.003 | 0.003 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.005 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".