UDC 378

Fulin V.A.¹ (Ryazan, Russian Federation) – v.fulin@rsu-rzn.ru; Kostikova L.P.^1,2 (Ryazan, Russian Federation) – l.p.kostikova@gmail.com; Yeltsov A.V.² (Ryazan, Russian Federation) – eltsov17@rambler.ru

¹Ryazan State University named after S.A. Yesenin

²Ryazan State Medical University named after Academician I. P. Pavlov of the Ministry of Health of the Russian Federation

Abstract. The spread of generative artificial intelligence (GenAI) built on large language models (LLMs) calls into question established forms of assessing humanities students’ learning outcomes. The multiplicity of interpretations, contextual dependence and value-laden character of humanities knowledge make it vulnerable to substitution by machine-generated texts, while it remains unclear how validity and reliability of assessment should be redefined, and what exactly is being evaluated – the student’s competencies or the quality of the model’s output. The aim is to identify the specifics of applying GenAI to assessing humanities students’ outcomes and to develop recommendations for integrating such technologies into university assessment practice. The methodological basis combines analysis of publications on pedagogical monitoring, computer-based testing and GenAI use in education with a comparison of LLM performance on humanities and natural-science tasks. The statistical nature of LLMs is shown to bias output toward conventional solutions, limit the handling of intertextuality and cultural context, and raise the risk of plausible but unfounded interpretations. A typology of assignments is proposed by their resistance to replacement by GenAI, ranging from reproductive essays and reports to oral assessment forms excluding external assistance. Recommendations are formulated for designing tasks grounded in students’ personal experience and local sources, legitimising GenAI use subject to mandatory disclosure of prompts, and shifting assessment focus from the finished text to the process of its creation and reflection on it. The results can be used by humanities faculty, developers of assessment tools and university units responsible for academic integrity when revising assessment formats.

Keywords: generative artificial intelligence, large language models, assessment of learning outcomes, humanities education, academic integrity, critical thinking, typology of assessment tools, validity of assessment, prompt engineering.

References:

1. Abakumova, N. N., Fakhrutdinova, A. V., Ju, C., & Lei, G. (2024). Pedagogical monitoring of innovative changes in higher education [Monograph]. Tomsk State University. (In Russian). https://elibrary.ru/snpibx
2. Abakumova, N. N., & Fakhrutdinova, A. V. (2026). Pedagogical monitoring of innovations and the paradox of unfixed assessment. In Man in modern socio-philosophical concepts: Proceedings of the X All-Russian scientific-practical conference (pp. 77–82). Kazan University Press. (In Russian). https://elibrary.ru/muhrpu  
3. Rypakova, V. G., & Fakhrutdinova, A. V. (2023). Features of assessing foreign language proficiency achievements in a mixed-level group. Teacher of the 21st Century, 2-1, 100–113. (In Russian). https://doi.org/10.31862/2073-9613-2023-2-100-113
4. Voevoda, E. V., & Evteev, S. V. (2024). Problems of creating a national system for assessing foreign language proficiency. The World of Science, Culture and Education, 6(109), 37–40. (In Russian). https://doi.org/10.24412/1991-5497-2024-6109-37-40
5. Solovov, A. V., & Menshikova, A. A. (2026). Didactics and artificial intelligence in the development and use of computer-based tests. Informatization of Education and Science, 69(1), 64–77. (In Russian).
6. Antipkina, I. V., Ivanushchenko, A. V., Kalabina, I. A., & Fulin, V. A. (2025). Tests as assessment tools in universities: Challenges and solutions. The World of Psychology, 4(123), 295–316. (In Russian). https://doi.org/10.51944/20738528_2025_4_295
7. Kostikova, L. P., Esenina, N. E., & Fulin, V. A. (2026). Generative artificial intelligence as a tool for creating educational and professional situations. CITISE, 1(47), 246–257. (In Russian). https://elibrary.ru/tgphjm
8. Solovov, A. V., & Menshikova, A. A. (2025). Ontology of computer-based testing in education. Ontology of Designing, 15(2)(56), 228–238. (In Russian). https://doi.org/10.18287/2223-9537-2025-15-2-228-238
9. Agaltsova, D. V., & Putilina, N. A. (2023). Testing in the educational process of a university: Features, tasks, and application formats. Humanities. Bulletin of the Financial University, 13(S1), 6–9. (In Russian). https://doi.org/10.26794/2226-7867-2023-13-c-6-9
10. Bezrukov, A. I., & Khvorostukhina, E. V. (2024). Instrumental and methodological support of intelligent testing systems. Informatization of Education and Science, 4(64), 46–53. (In Russian). https://elibrary.ru/fdhxpp
11. Talov, D. P., & Tarasova, K. V. (2026). Assessment of university students’ critical thinking: The contribution of subject knowledge to test results. Higher Education in Russia, 35(4), 85–104. (In Russian). https://doi.org/10.31992/0869-3617-2026-35-4-85-104
12. Gulov, A. P., Yudin, N. O., Chigasheva, M. A., et al. (2026). The impact of AI tools on the development of foreign language speaking skills and digital competence: A longitudinal study and assessment matrix. Higher Education in Russia, 35(3), 90–113. (In Russian). https://doi.org/10.31992/0869-3617-2026-35-3-90-113
13. Akhrenova, N. A., & Yatskina, K. V. (2026). A model of digital diagnostics of educational trajectories in higher education: Results of a quasi-experimental study. Higher Education in Russia, 35(4), 126–145. (In Russian). https://doi.org/10.31992/0869-3617-2026-35-4-126-145
14. Menshenina, S. G., & Kosharskaya, E. V. (2026). The role of the teacher in an interactive foreign language learning environment using AI chatbots. CITISE, 2, 638–646. (In Russian).
15. Bogolepova, S. V., & Smirnova, A. G. (2026). Artificial intelligence as a tool for differentiation in foreign language teaching. Foreign Languages at School, 4, 5–11. (In Russian). https://elibrary.ru/mwxcgr
16. Evstigneev, M. N., Evstigneeva, I. A., & Chetyrina, N. V. (2026). Development of learners’ foreign language mediation skills through interactive practice with artificial intelligence technologies. Foreign Languages at School, 4, 12–20. (In Russian). https://elibrary.ru/glgxra
17. Abdulmyanova, I. R. (2026). A chatbot as a tool for increasing the interactivity of an instructional package on foreign language teaching methodology. Foreign Languages at School, 4, 61–68. (In Russian). https://elibrary.ru/wavfdp
18. Popova, A. V. (2026). Pedagogical prompt engineering: Designing queries in accordance with didactic principles. Foreign Languages at School, 4, 40–47. (In Russian). https://elibrary.ru/uzpqwh
19. Davlatova, M. A., & Speranskaya, M. V. (2026). Prompt engineering as a key competence in education: Essence, features, and approaches to assessment. Higher Education in Russia, 35(2), 53–73. (In Russian). https://doi.org/10.31992/0869-3617-2026-35-2-53-73

For citation: Fulin, V. A., Kostikova, L. P., & Yeltsov, A. V. (2026). Assessing educational outcomes of humanities students through generative AI technologies. CITISE, 3, 102-116. (In Russian).