Gamification of Literary Classics Using Large Language Models: Developing a Digital Assistant for the Secondary School Literature Course

Herald of the Russian Academy of Sciences. 2026. No. 96. P. 24–32.

Kolmogorova A., Seredina D. A.

The relevance of this study is determined by the challenge of integrating large language models (LLMs) into language pedagogy, specifically for gamifying the process of studying Russian classical literature and fostering reading motivation among high school students. This study aims to develop and test a digital assistant, powered by an LLM, designed to gamify the study of Russian classical literature in a secondary school setting. The research assesses the effectiveness of this tool and its perceived appeal among the target audience. The core technological stack was built upon the method of strategic LLM prompting and the retrieval-augmented generation (RAG) method, incorporating elements of semantic search. The research methodology employed a survey combined with focused beta-testing: a test version of the LLM-integrated chatbot was provided to a focus group (high school students preparing for the Unified State Exam in Literature and their teacher) for a limited period. Focus group participants completed surveys both before and after the beta-testing phase. The study demonstrated the efficacy of the proposed technological pipeline for: a) generating fan literature based on texts of Russian classical literature, b) generating questions aimed at fostering students' comprehension of the content and meaning of Russian classical literary texts, and c) creating a recommendation system to facilitate the discovery of texts based on their themes and to identify semantically correlated contemporary films for literary works. The obtained results indicate that through the application of diverse prompting approaches and functional enhancement via RAG, the chatbot evolves beyond a mere LLM interface into a fully-fledged, specialised service for addressing specific tasks in digital language didactics.

Keywords: semantic search, school education, large language models, prompting, retrieval-augmented generation

Publication based on the results of: Linguistic and cognitive diversity in formal models, computer tools, and educational resources (2025)