Assessing complexity of educational texts of Russian as a foreign language: Prospects and challenges of using artificial intelligence

The growing interest in Russian education, culture, and science results in the pressing demand for tools to select educational texts for Russian as a foreign language. The study is aimed at working out the algorithm and instruments for assessing the lexical complexity of text in Russian as a foreign language on CEFR with the help of LLM. The study is based on the material of a training sample, including standardized lexical minima in Russian as a foreign language and 232 texts ranked in difficulty by experts, and a test sample with 14 texts for listening in Russian as a foreign language. The methods of computational linguistics (Python script process_word_lists, LLM), expert assessment and metrics for statistical evaluation of the quality of classification models were used in the work. The study describes the successfully used large language models to assess the complexity of Russian-language texts on the RuLingva platform. The results of the study include the created linguistic profiles and the identified abilities of the large GLM 4.6 and Grok 4 fast language models to assess the complexity of educational texts in Russian as a foreign language (A1-C1). The proposed algorithm ranks texts by complexity with a high degree of accuracy, develops test tasks and selects texts for textbooks on Russian as a foreign language. The results obtained can be used by teachers in Russian as a foreign language, testologists, and linguists for preparing teaching materials, glossaries, and test assignments. The prospect of the work is to improve the developed algorithm by expanding the corpus and applying classification models for texts of different genres.