Automatic story and item generation for reading comprehension assessments with transformers
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Reading comprehension is one of the essential skills for students as they make a transition from learning to read to reading to learn. Over the last decade, the increased use of digital learning materials for promoting literacy skills (e.g., oral fluency and reading comprehension) in K-12 classrooms has been a boon for teachers. However, instant access to reading materials, as well as relevant assessment tools for evaluating students’ comprehension skills, remains to be a problem. Teachers must spend many hours looking for suitable materials for their students because high-quality reading materials and assessments are primarily available through commercial literacy programs and websites. This study proposes a promising solution to this problem by employing an artificial intelligence (AI) approach. We demonstrate how to use advanced language models (e.g., OpenAI’s GPT-2 and Google’s T5) to automatically generate reading passages and items. Our preliminary findings suggest that with additional training and fine-tuning, open-source language models could be used to support the instruction and assessment of reading comprehension skills in the classroom. For both automatic story and item generation, the language models performed reasonably; however, the outcomes of these language models still require a human evaluation and further adjustments before sharing them with students. Practical implications of the findings and future research directions are discussed.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 it