Automated Assessment of Cognitive Levels in Bloom’s Taxonomy Through RAG-Based Architecture with LLMs
Open Access
- 17 July 2026
- conference paper
- Published by MDPI AG in Engineering Proceedings
- Vol. 150 (1) , 17
Abstract
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.Keywords
This publication has 12 references indexed in Scilit:
- Automated Grading of Open-Ended Questions in Higher Education Using GenAI ModelsInternational Journal of Artificial Intelligence in Education, 2025
- Using ChatGPT to score essays and short-form constructed responsesAssessing Writing, 2025
- Automated scoring in the era of artificial intelligence: An empirical study with Turkish essaysSystem, 2025
- Evaluating LLMs for Automated Scoring in Formative AssessmentsApplied Sciences, 2025
- LLM-based automatic short answer grading in undergraduate medical educationBMC Medical Education, 2024
- Harnessing LLMs for multi-dimensional writing assessment: Reliability and alignment with human judgmentsHeliyon, 2024
- E-learning application in english writing classroom based on neural machine translation and semantic analysis algorithmsEntertainment Computing, 2024
- Large language models and automated essay scoring of English language learner writing: Insights into validity and reliabilityComputers and Education: Artificial Intelligence, 2024
- Automatic evaluation of open-ended questions for online learning. A systematic mappingStudies in Educational Evaluation, 2023
- Automatic grading and hinting in open-ended text questionsCognitive Systems Research, 2020