A Review of Automatic Item Generation Techniques Leveraging Large Language Models
Bibliographic record
Abstract
Over a decade ago, automatic item generation (AIG) was introduced to meet the increasing need for high-quality items in educational measurement. Around the same time, a new area of research in computer science began to develop questions for educational use. Historically, researchers from these two domains had little knowledge or communication with one another. However, the development of pre-trained large language models (LLMs) has sparked the interest of researchers from both domains in applying these models for automatically creating items. With similar objectives and methodologies, these two research domains appear to be converging on how to address the problems in this field. The purpose of this study is to provide a review of the current state of research by synthesizing existing studies on the use of LLMs for AIG. By combining research from both domains, we examine the utility and potential of LLMs for AIG. We performed a comprehensive literature review in seven research databases, selected studies based on predefined criteria, and summarized 60 relevant studies that employed LLMs in the AIG process. We identified the most commonly used LLMs in current AIG literature, their specific applications in the AIG process, and the characteristics of the generated items. We found that LLMs are flexible and effective in generating various types of items based on different languages and subject domains. However, many studies have overlooked the quality of the generated items, indicating a lack of a solid educational foundation. This review emphasizes the urgent need for greater integration of learning and measurement theories in future AIG research. We share two suggestions to enhance the educational foundation for leveraging LLMs in AIG, advocating for interdisciplinary collaborations to exploit the utility and potential of LLMs.
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 | 0.022 | 0.072 |
| Meta-epidemiology (narrow) | 0.003 | 0.002 |
| Meta-epidemiology (broad) | 0.003 | 0.004 |
| Bibliometrics | 0.013 | 0.012 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.004 |
| Open science | 0.004 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.006 | 0.004 |
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".