• A
  • A
  • A
  • АБВ
  • АБВ
  • АБВ
  • A
  • A
  • A
  • A
  • A
Обычная версия сайта
  • RU
  • EN
  • HSE University
  • Publications
  • Articles
  • Large Language Model-Based Automated Item Generation in STEM Assessments: Historical Mapping and a Scoping Review of Empirical Studies
  • RU
  • EN
Расширенный поиск
Высшая школа экономики
Национальный исследовательский университет
Priority areas
  • business informatics
  • economics
  • engineering science
  • humanitarian
  • IT and mathematics
  • law
  • management
  • mathematics
  • sociology
  • state and public administration
by year
  • 2027
  • 2026
  • 2025
  • 2024
  • 2023
  • 2022
  • 2021
  • 2020
  • 2019
  • 2018
  • 2017
  • 2016
  • 2015
  • 2014
  • 2013
  • 2012
  • 2011
  • 2010
  • 2009
  • 2008
  • 2007
  • 2006
  • 2005
  • 2004
  • 2003
  • 2002
  • 2001
  • 2000
  • 1999
  • 1998
  • 1997
  • 1996
  • 1995
  • 1994
  • 1993
  • 1992
  • 1991
  • 1990
  • 1989
  • 1988
  • 1987
  • 1986
  • 1985
  • 1984
  • 1983
  • 1982
  • 1981
  • 1980
  • 1979
  • 1978
  • 1977
  • 1976
  • 1975
  • 1974
  • 1973
  • 1972
  • 1971
  • 1970
  • 1969
  • 1968
  • 1967
  • 1966
  • 1965
  • 1964
  • 1963
  • 1958
  • More
Subject
News
November 17, 2026
Physicists Show How a Solvent Shapes the Response of Drug Molecules
Many drug molecules can switch between different three-dimensional shapes. Using a mathematical model of ibuprofen dissolved in supercritical CO₂, researchers from HSE University and the Institute of Solution Chemistry of the Russian Academy of Sciences have shown that the solvent can make these molecules appear to respond unusually slowly. The molecules themselves continue to change shape rapidly, but their surroundings rearrange much more slowly, and this lag shows up in the measurements. The study has been published in The Journal of Chemical Physics. 
November 10, 2026
Physicists Train AI to Optimise Particle Beams in Accelerators
Researchers from the AI and Digital Science Institute at the HSE Faculty of Computer Science and the Budker Institute of Nuclear Physics at the Siberian Branch of the Russian Academy of Sciences have developed RLABC (Reinforcement Learning for Accelerator Beamline Control), a framework that uses reinforcement learning to identify optimal settings for a particle accelerator. In a computer simulation, RLABC optimised the accelerator's parameters to achieve a particle transmission rate of 70%. The study has been published in Computer Physics Communications.
November 9, 2026
'Organ-on-a-Chip Technology Could Eliminate the Need for Animal Testing'
The Laboratory of Molecular Physiology at the HSE Faculty of Biology and Biotechnology investigates how molecular regulators known as microRNAs control gene expression and contribute to the development of diseases, including cancer, viral and inflammatory conditions, and pregnancy complications. At HSE University, researchers develop organ-on-a-chip models: miniature devices containing living cells that mimic the functions of human organs, such as the placenta and intestines. These models help researchers understand how diseases develop and how drugs affect them. HSE News Service spoke with Evgeny Knyazev, Head of the Laboratory.

 

Have you spotted a typo?
Highlight it, click Ctrl+Enter and send us a message. Thank you for your help!

Publications
  • Books
  • Articles
  • Chapters of books
  • Working papers
  • Report a publication
  • Research at HSE

?

Large Language Model-Based Automated Item Generation in STEM Assessments: Historical Mapping and a Scoping Review of Empirical Studies

JOURNAL OF EDUCATIONAL TECHNOLOGY DEVELOPMENT AND EXCHANGE. 2026. Vol. 19. No. 2. P. 141–165.
Omopekunola M.

Educational assessments, from low-stakes classroom tests to high-stakes national examinations, require item pools that are valid, fair, and secure. Automated Item Generation (AIG) aims to efficiently produce large pools of calibrated test items. This paper adopts a two-part design: (1) a brief historical mapping situating LLM-based AIG within the broader AIG trajectory; and (2) a scoping review of empirical studies on LLM-based AIG for STEM assessments, published between January 2022 and January 2026. A structured search of ERIC, Lens and OpenAlex yielded 1,267 records; after deduplication and screening, 7 studies were retained for synthesis. In all studies, LLMs were primarily used to draft stems, keys, distractors, and explanations by instruction-tuned prompting, sometimes enhanced with retrieval and human-in-the-loop review. Empirical evidence on item quality is generally promising. Multiple investigations have documented acceptable expert evaluations and, in a subset of studies, psychometric properties comparable to those of human-authored items. Nevertheless, recurrent limitations have been observed, including factual inaccuracies, construct drift, low calibration of item difficulty, and variable distractor plausibility. Few studies reported robust fairness audits or provided reproducible details, such as complete prompts and decoding settings. In general, LLM-based AIG can substantially increase throughput in STEM item development, but high-stakes deployment requires layered validation protocols (expert review, pilot testing, psychometrics, and bias audits) and governance controls to ensure traceability and item security.

Research target: Education Psychology
Language: English
DOI
Text on another site
Keywords: automated item generationLarge language models (LLM)prompt engineeringHigh-stakes assessmentPsychometric validation
Similar publications
Oculomotor and stimulus-locked ERP responses during an emotional antisaccade task in obsessive-compulsive disorder
Khayrullina G., Safronov P., Liaukovich K. et al., Frontiers in Systems Neuroscience 2026 Vol. 20 P. 1959377
Added: November 19, 2026
Практическое руководство по написанию аргументативных эссе на английском языке. A Practical Guide to Writing Argumentative Essays in English.
Voronina Y., Kuryan M., Н. Новгород: Нижегородский государственный технический университет им. Р.Е. Алексеева, 2026.
Modern foreign-language teaching is aimed at developing not only language skills but also the ability to organise and expres ideas logically and present one’s own position with well-supported arguments. In this context, academic writing is particularly important because it helps learners develop critical thinking, analyse information, compare different points of view, and support their conclusions with convincing ...
Added: November 18, 2026
Atypical neural activation and age-related patterns in dyslexia
Samoylov I., Bolgina T., Georgii L. et al., Cerebral Cortex 2026 Vol. 36 No. 8
This magnetoencephalography study investigated the spatiotemporal neural responses during single-word reading. We used a silent reading task with linguistic stimuli varying in lexicality and frequency (high- and low-frequency words, and pseudowords), and tested typically developing (TD) and dyslexic developing (DD) children (aged 7 to 12). We observed no significant sensitivity to word frequency or lexicality ...
Added: November 17, 2026
Investigating the association between session quality and nonverbal synchrony in psychological counseling
Сухоруков С. Д., Орешина Г. В., Жукова М. А. et al., Vestnik of Saint Petersburg University. Psychology 2026 Vol. 16 No. 3 P. 510–523
Session quality is one of the key process variables in psychotherapy and counseling. It is often assessed via self-reports by clients and counselors. Concurrently, nonverbal synchrony — the temporal coordination of body movements — has been suggested as an objective behavioral indicator of relational attunement. However, the findings regarding its correlation with ses-sion quality remain ...
Added: November 16, 2026
Agentic Large Language Models for Multimodal Item Generation and Automated Review in Educational Assessment: A Framework Using Kazakhstan’s UNT Physics Test
Shinetova L., Omopekunola M., Kardanova E. et al., Sage Open 2026 Vol. 16 No. 4
High-stakes educational assessment requires large numbers of high-quality items, yet item writing and review remain labor-intensive, especially when items include visual stimuli. This study presents a descriptive feasibility evaluation of an agentic large language model (LLM) framework implemented as a role-based, multi-stage LLM orchestration workflow for generating and reviewing multimodal physics multiple-choice items for Kazakhstan’s ...
Added: November 14, 2026
О чем говорит школьный урок? Корпусный анализ структуры урока и речи учителя как основа для педагогических продуктов
Виноградова Ю. С., Браташ В. С., Zubov V. et al., Вопросы образования 2026 Т. 1 № 3 С. 94–131
The aim of the study is to describe the structure of a school lesson and identify linguistic characteristics associated with effective teaching practices, based on recordings of real lessons in schools of the Russian Federation. Fifty-five audio recordings of lessons (Grades 5–9, six subjects, 2022–2024) were annotated for lesson structure, phonetic, lexical, and grammatical features, ...
Added: November 13, 2026
РУССКОЯЗЫЧНАЯ АДАПТАЦИЯ ОПРОСНИКА ВОЗРАСТНОГО КРИЗИСА (ОВК–РУС) НА ПРИМЕРЕ КРИЗИСА ПЕРВОЙ ЧЕТВЕРТИ ЖИЗНИ
Yerofeyeva V., Nartova-Bochaver S. K., Вопросы психологии 2026 Т. 72 № 2 С. 105–114
The article presents the results of the adaptation of the Developmental Crisis Questionnaire (DCQ–Rus) in Russia (N = 335) using the case of the quarter-life crisis experienced by emerging adults (from 18 to 29 years). At this time, there is an active development of identity and personal authenticity, and the demands of the external environment ...
Added: November 13, 2026
Cultural Variability in the Link Between Affect and Meaning in Life: Evidence From 69 Countries.
Górski M., Costin V., van Tilburg W. et al., Emotion 2026 P. 1–21
People tend to evaluate their lives as more meaningful when they experience morepositive affect and lessnegative affect. However, most evidence for this association comes from Western, educated, industrialized, rich, and democratic societies, which are culturally distinctive in their strong emphasis onhappiness. To assess the cross-cultural generality of the affect–meaning link, we conducted the largest cross-cultural ...
Added: November 13, 2026
ПОКОЛЕНИЕ «АЛЬФА»: разговоры о важном
Бакушина А. Н., Роща, 2026.
Поколение «альфа»: разговоры о важном. Размышления после круглого стола. Материалы педагогической дискуссии 14 мая 2026 г. / составитель — А. Н. Бакушина ...
Added: November 13, 2026
Model-Dependent Prompt-Component Ablation for Medical LLM Decision Support: Application to ENT Biologics Screening
Sergey N. Koltcov, Budkovaia M., Surkov A. et al., IEEE Journal of Biomedical and Health Informatics 2026 P. 1–10
Large language models (LLMs) show promise for clinical decision support, but privacy constraints and unreliable free-text decisions limit deployment. We present Medotor, a locally deployed system for screening patients with chronic rhinosinusitis with nasal polyps (CRSwNP) for biologic therapy, and evaluate prompt design on 163 retrospective cases (132 eligible and 31 ineligible). Five models were ...
Added: November 13, 2026
Психологческая помощь семье, Ориентированный на решение подход.
Берг И. К., M.: Cogito-Centre–IPRAS Publishing House, 2026.
In the book Psychological Assistance to Families: A Solution-Focused Approach, one of the founders of Solution-Focused Brief Therapy Insoo Kim Berg presents this approach through the lens of helping families facing difficult life circumstances, which often affect the well-being and sometimes even the safety of children. The core principles of the approach are to build collaboration, to drawi on clients’ ...
Added: November 12, 2026
Choosing Between AI Responses: How Valence, Arousal, and Dominance Shape User Preference
Parshakov P., Paklina S., International Journal of Human-Computer Interaction 2026 P. 1–17
This study examines how emotional tone shapes user preference in human–large language model (LLM) interaction. Drawing on the Computers as Social Actors framework, we treat conversational AI as a social communicator whose affective cues influence user judgments. Using large-scale pairwise preference data from LMSYS Chatbot Arena, we model emotional tone through the Valence–Arousal–Dominance framework and ...
Added: September 23, 2026
LLM-assisted writing and citation advantage: evidence from scientific publications before and after ChatGPT release
Paklina S., Parshakov P., Elena Rapoport, Scientometrics 2026 No. 131 P. 7611–7636
Generative artificial intelligence has become a routine part of academic writing. While much of the debate has focused on questions of integrity and authorship, less attention has been paid to how AI-assisted writing may affect research evaluation itself. This paper asks a straightforward but important question: does the use of LLMs in academic writing change ...
Added: September 23, 2026
Comparing Large Language Models for Aspect-Based Sentiment Analysis of Student Experience from Russian-Language Online Course Reviews
Kalicheva V., Kirina M., , in: Speech and Computer. 28th International Conference, SPECOM 2026, Ohrid, North Macedonia, September 17–18, 2026, Proceedings, Part I.: Springer, 2026. P. 320–337.
The rapid expansion of the online education market has produced large volumes of unstructured data—course reviews containing detailed evaluations of specific educational components. Aspect-based sentiment analysis (ABSA) makes it possible to move from a holistic assessment of the educational experience to an analysis of its individual constituents, identifying particular aspects of learning and students’ attitudes ...
Added: September 20, 2026
The development of an interface for teaching virtual assistant based on function-calling and prompt engineering technologies
Firsanova V.I., Человек: образ и сущность. Гуманитарные аспекты 2025 No. 2(62) P. 203–214
Abstract. The paper highlights prompt engineering in academic setting to reduce plagiarism and increase students' interest. The research problem is the lack of a unified methodology for using artificial intelligence in education. The paper aims to create a generative artificial intelligence user interface, the Virtual Teaching Assistant. Teachers were interviewed, the first collection of presets ...
Added: September 9, 2026
Development and validation of the Mental Health Self-Care Scale for the general adult population
Mikhaylova O., Zhyrgalbek J., Sofia Yanis et al., Public Health 2026 Vol. 258 Article 106405
Objectives: To develop and psychometrically validate the Mental Health Self-Care Scale (MHSCS) for assessing mental health self-care behaviours in the general adult population. Study design: Cross-sectional survey. Methods: A 62-item initial pool grounded in the updated Middle Range Theory of Self-Care was refined through expert review (n = 11) and cognitive interviewing (n = 24), then administered to 600 Russian ...
Added: June 25, 2026
Use Case 5: LLM-driven creation of natural hazard geodatabase from digital mass media
Derkacheva A., Sakirkina M., Kraev G. et al., , in: AI for good innovate for impact report 2025.: Geneva: International Telecommunication Union, 2025. P. 167–169.
Added: May 26, 2026
Large Language Model-Based Automated Item Generation in STEM Assesements: Historical Mapping and a Scoping Review of Empirical Studies
Omopekunola M., JOURNAL OF EDUCATIONAL TECHNOLOGY DEVELOPMENT AND EXCHANGE 2026 Vol. 19 No. 2 P. 141–165
Educational assessments, from low-stakes classroom tests to high-stakes national examinations, require item pools that are valid, fair, and secure. Automated Item Generation (AIG) aims to efficiently produce large pools of calibrated test items. This paper adopts a two-part design: (1) a brief historical mapping situating LLM-based AIG within the broader AIG trajectory; and (2) a ...
Added: May 5, 2026
Об идеологических предвзятостях генеративного ИИ: Российско-украинский конфликт в репрезентации ChatGPT
Baysha O., Trofimov V., Российская школа связей с общественностью 2026 № 40 С. 171–191
A growing number of scholars are warning about the dangers of the reproduction by generative AI of socio-political and ideological biases absorbed by models from the texts on which they were trained. If a given model was trained on Western media texts, it may generate narratives that reproduce West centric views of world events. This ...
Added: April 21, 2026
Сопоставление номенклатур товаров ресторанов и поставщиков с помощью LLM — Case Study для ресторанного холдинга
Jin S., Panfilov P., Sulejkin A., Труды Института системного программирования РАН 2025 Т. 37 № 6 С. 163–176
In the modern restaurant business, accurate mapping of product nomenclatures between restaurants and suppliers is a critical task. Effective inventory management and procurement optimization directly impact business profitability. With the increase in suppliers and product variety, traditional mapping methods become less efficient. This study proposes using large language models (LLM) to automate and improve the ...
Added: April 17, 2026
Learning When to Personalize: LLM Based Playlist Generation via Query Taxonomy and Classification
Buzaev F., Пугачёва Д. В., Sukharev I. et al., Transactions of the Association for Computational Linguistics 2026 P. 51–57
Playlist generation based on textual queries using large language models (LLMs) is becoming an important interaction paradigm for music streaming platforms. User queries span a wide spectrum from highly personalized intent to essentially catalog-style requests. Existing systems typically rely on non-personalized retrieval/ranking or apply a fixed level of preference conditioning to every query, which can ...
Added: April 7, 2026
Large Language Models as Political Actors: Cultural Bias and Epistemic Power
Seredkina E., Seletkova G., Mikhailovsky A., Technology and Language 2026 Vol. 7 No. 1 P. 63–79
The rapid diffusion of Large Language Models (LLMs) into socially and politically sensitive domains raises critical questions about the nature and origins of political bias in artificial intelligence. While existing research often treats bias as a technical flaw to be minimized, this article advances a broader philosophical and cultural interpretation of LLM bias as an ...
Added: April 1, 2026
Validating the Russian Adult Prosocialness Behavior Scale: Weighted Factor Analysis, Sex Invariance, and Normative Benchmarks
Mikhaylova Oxana, Bochaver Alexandra, Current Psychology 2026 Vol. 45 Article 712
Prosocial behavior measures validated across diverse cultural contexts remain limited. We validated the Adult Prosocialness Behavior Scale (APBS) in 7,965 Russian adults (52.0% women; Mage = 42.4, SD = 12.1) using sampling weights to approximate population representativeness. Split-sample analyses supported a two-factor structure with correlated Prosocial Actions and Prosocial Feelings dimensions (χ² = 2,754.87, CFI = .978, TLI ...
Added: March 11, 2026
Промпт-инжиниринг как ключевая компетенция в образовании: сущность, особенности и подходы к оцениванию
Davlatova M., Сперанская М. В., Высшее образование в России 2026 Т. 35 № 2 С. 53–73
In the context of the rapid development of Generative Artificial Intelligence (GenAI), prompt engineering is becoming a key competence for effective interaction with large language models in educational settings. However, the lack of a unified understanding of its nature, structure, and assessment tools complicates its integration into educational practice.    The aim of this study is to ...
Added: March 7, 2026
  • About
  • About
  • Key Figures & Facts
  • Sustainability at HSE University
  • Faculties & Departments
  • International Partnerships
  • Faculty & Staff
  • HSE Buildings
  • HSE University for Persons with Disabilities
  • Public Enquiries
  • Studies
  • Admissions
  • Programme Catalogue
  • Undergraduate
  • Graduate
  • Exchange Programmes
  • Summer University
  • Summer Schools
  • Semester in Moscow
  • Business Internship
  • Research
  • International Laboratories
  • Research Centres
  • Research Projects
  • Monitoring Studies
  • Conferences & Seminars
  • Academic Jobs
  • Yasin (April) International Academic Conference on Economic and Social Development
  • Media & Resources
  • Publications by staff
  • HSE Journals
  • Publishing House
  • iq.hse.ru: commentary by HSE experts
  • Library
  • Economic & Social Data Archive
  • Video
  • HSE Repository of Socio-Economic Information
  • HSE1993–2026
  • Contacts
  • Copyright
  • Privacy Policy
  • Site Map
Edit