ArticleFrontiers in big data2026
Generation of Kazakhstan's unified national testing variants using AI: a platform for automatic task creation with expert control.
Article in Frontiers in big data, 2026. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Not yet cited in PubMed.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
0 citing papers in PubMed.
No citing paper in PubMed yet.
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
6 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
This study examines the use of artificial intelligence for Automatic Item Generation (AIG) in the context of Kazakhstan's Unified National Testing (UNT) and presents a human-in-the-loop platform for scalable, expert-controlled test development. The objective is to evaluate whether large language models (LLMs) can reliably generate high-quality, isomorphic mathematics test items in the Kazakh language while preserving psychometric and pedagogical requirements. A hybrid AI system combining a local and a cloud-based LLM was implemented to perform semantic deconstruction of prototype items and constrained isomorphic generation of new variants. The pipeline included structured prompt engineering, parallel generation, and automated symbolic validation using Python and SymPy, followed by double-blind expert review. A stratified sample of 120 UNT mathematics items served as prototypes, from which 200 AI-generated clones were produced and validated. Six qualified subject-matter experts conducted independent evaluations using standardized criteria. Inter-rater reliability reached a substantial level (Cohen's κ = 0.78). Results show that 97.5% of generated items were recommended for use after review, with 50.5% accepted without revision and 47.0% accepted after corrections. The most frequent revision needs involved difficulty calibration, wording clarity, and factual or curricular alignment. Expert interviews confirmed that AI generation significantly reduces development time but remains limited in higher-order cognitive item design and pedagogically grounded distractor construction, especially in a low-resource, morphologically complex language environment. The findings support a hybrid augmentation model in which AI accelerates large-scale item production while experts ensure linguistic, cultural, and psychometric validity. The proposed framework demonstrates practical potential for multilingual, high-stakes assessment systems and provides implementation guidelines for responsible AI integration in test development.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.