LARGE LANGUAGE MODELS IN SOLVING PEDAGOGICAL PROBLEMS

Author(s): Krichevsky M.L.

Rubric: Information technology

DOI: 10.21777/2500-2112-2025-2-102-111

Release: 2025-2 (51)

Pages: 102-111

Keywords: generative artificial intelligence, large language model, machine learning, deep learning, preparation of educational materials

Annotation: The article examines large language models in the context of automation of routine pedagogical tasks. A brief analysis of the tasks that arise during the work of a higher school teacher is carried out, and the most important problems that can be solved using artificial intelligence methods are highlighted. The concept of artificial intel- ligence is presented and described, which includes machine learning, deep learning and generative artificial intelligence as constituent elements. The evolution of large language models that belong to the field of generative artificial intelligence and are characterized by the ability to create text, images, code and audio is shown. The results of the transformation of large language models from the moment of their emergence to the appearance of the latest models are presented. The possibilities of using the Russian large GigaChat-type language model in the educational process are shown, ways of application are indicated and further plans are outlined. Attention is drawn to the limitations of the use of generative models in the educational process related to the manifestation of hallucinations of large language models and the thoroughness of the query.

Bibliography: Krichevsky M.L. LARGE LANGUAGE MODELS IN SOLVING PEDAGOGICAL PROBLEMS // Education Resources and Technologies. – 2025. – № 2 (51). – С. 102-111. doi: 10.21777/2500-2112-2025-2-102-111