Using Large Language Models to Create Educational Materials for the “Databases†Discipline

A. D. Asenchik ()

Digital Transformation, 2025, vol. 31, issue 4

Abstract: This paper examines the use of large language models (LLM) for creating educational materials. A practical methodology for generating high-quality educational content for the speciï¬ c discipline of “Databases†is proposed and veriï¬ ed. A multi-stage methodology is presented, in which one LLM generates content, and a second, independent “reasoning†model veriï¬ es its quality and correctness. A comparison method with an authoritative source and a modiï¬ ed “veriï¬ cation chain†algorithm was used to check the generated materials for factual errors. The results conï¬ rm that this approach, when used with modern, high-performance LLMs (such as DeepSeek and Gemini), enables the creation of high-quality educational texts with a low probability of hallucinations. The methodology can signiï¬ cantly accelerate the development of reliable educational materials and can be optimized by reducing the number of iterations while maintaining a high-quality initial response.

Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://dt.bsuir.by/jour/article/viewFile/966/368 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:abx:journl:y:2025:id:966

DOI: 10.35596/1729-7648-2025-31-4-5-14

Access Statistics for this article

More articles in Digital Transformation from Educational Establishment “Belarusian State University of Informatics and Radioelectronicsâ€
Bibliographic data for series maintained by Ð ÐµÐ´Ð°ÐºÑ†Ð¸Ñ ().