Autors: Vangelova A., Gancheva, V. S.
Title: Automated Assessment of Cognitive Levels in Bloom’s Taxonomy Through RAG-Based Architecture with LLMs †
Keywords: analytical rubric, automated grading, Bloom’s Taxonomy, e-learning, LLM, Moodle, open-ended questions, RAGAbstract: This paper presents a RAG-based architecture with a large language model for automated assessment of student responses, in which Bloom’s Taxonomy is used to structure an analytical rubric and to form a cognitive profile of the performance. The approach integrates Moodle, n8n, a vector database for semantic retrieval of relevant context, and a GPT model for criterion-based assessment. The model’s output is formed based on the student response, the RAG-extracted learning context, and a predefined rubric. The system is implemented in a real exam environment in Bulgarian and English. The results of data analysis show differentiated behavior across Bloom’s cognitive levels, with higher sensitivity in tasks related to remembering, understanding, and applying, and more conservative behavior in tasks related to evaluating and critical thinking. Expert evaluation of the automatically generated feedback confirms its clarity, usefulness, and correctness. References - Grévisse C. LLM-based automatic short answer grading in undergraduate medical education BMC Med. Educ. 2024 24 1060 10.1186/s12909-024-06026-5 39334087
- Sychev O. Anikin A. Prokudin A. Automatic grading and hinting in open-ended text questions Cogn. Syst. Res. 2020 59 264 272 10.1016/j.cogsys.2019.09.025
- Tang X. Chen H. Lin D. Li K. Harnessing LLMs for multi-dimensional writing assessment: Reliability and alignment with human judgments Heliyon 2024 10 e34262 10.1016/j.heliyon.2024.e34262 39113951
- Aydın B. Kışla T. Elmas N.T. Bulut O. Automated scoring in the era of artificial intelligence: An empirical study with Turkish essays System 2025 133 103784 10.1016/j.system.2025.103784
- Wang Y. E-learning application in english writing classroom based on neural machine translation and semantic analysis algorithms Entertain. Comput. 2024 51 100730 10.1016/j.entcom.2024.100730
- Pack A. Barrett A. Escalante J. Large language models and automated essay scoring of English language learner writing: Insights into validity and reliability Comput. Educ. Artif. Intell. 2024 6 100234 10.1016/j.caeai.2024.100234
- Pecuchova J. Benko Ľ. Drlik M. Automated Grading of Open-Ended Questions in Higher Education Using GenAI Models Int. J. Artif. Intell. Educ. 2025 35 3813 3846 10.1007/s40593-025-00517-2
- Jauhiainen J.S. Guerra A.G. Evaluating Students’ Open-ended Written Responses with LLMs: Using the RAG Framework for GPT-3.5, GPT-4, Claude-3, and Mistral-Large Adv. Artif. Intell. Mach. Learn. 2024 4 3097 3113 10.54364/AAIML.2024.44177
- García-Varela F. Nussbaum M. Mendoza M. Martínez-Troncoso C. Bekerman Z. ChatGPT as a Stable and Fair Tool for Automated Essay Scoring Educ. Sci. 2025 15 946 10.3390/educsci15080946
- Shermis M.D. Using ChatGPT to score essays and short-form constructed responses Assess. Writ. 2025 66 100988 10.1016/j.asw.2025.100988
- Del Gobbo E. Guarino A. Cafarelli B. Grilli L. Limone P. Automatic evaluation of open-ended questions for online learning. A systematic mapping Stud. Educ. Eval. 2023 77 101258 10.1016/j.stueduc.2023.101258
- Mendonça P.C. Quintal F. Mendonça F. Evaluating LLMs for Automated Scoring in Formative Assessments Appl. Sci. 2025 15 2787 10.3390/app15052787
- Bloom B.S. Engelhart M.D. Furst E.J. Hill W.H. Krathwohl D.R. Taxonomy of educational objectives: The classification of educational goals Handbook I: Cognitive Domain David McKay New York, NY, USA 1956
- Anderson L.W. Krathwohl D.R. A Taxonomy for Learning, Teaching, and Assessing: A Revision of Bloom’s Taxonomy of Educational Objectives Longman New York, NY, USA 2001
Issue
| Engineering Proceedings, vol. 150, 2026, Switzerland, https://doi.org/10.3390/engproc2026150017 |
|
