loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Toward Automated UML Diagram Assessment: Comparing LLM-Generated Scores with Teaching Assistants

Topics: Architectures for AI-based Educational Systems; Emerging Technologies in Education for Sustainable Development; Feedback and Learning Support; Intelligent Learning and Teaching Systems; Learning Analytics and Educational Data Mining; Metrics and Performance Measurement; Natural Language Processing; Next Generation Teaching and Learning Environments

Authors: Nacir Bouali ; Marcus Gerhold ; Tosif Ul Rehman and Faizan Ahmed

Affiliation: Department of Computer Science, University of Twente, The Netherlands

Keyword(s): AI-Assisted Grading, Autograding, Large Language Models, GPT, Llama, Claude, UML.

Abstract: This paper investigates the feasibility of using Large Language Models (LLMs) to automate the grading of Unified Modeling Language (UML) class diagrams in a software design course. Our method involves carefully designing case studies with constraints that guide students’ design choices, converting visual diagrams to textual descriptions, and leveraging LLMs’ natural language processing capabilities to evaluate submissions. We evaluated our approach using 92 student submissions, comparing grades assigned by three teaching assistants with those generated by three LLMs (Llama, GPT o1-mini, and Claude). Our results show that GPT o1-mini and Claude Sonnet achieved strong alignment with human graders, reaching correlation coefficients above 0.76 and Mean Absolute Errors below 4 points on a 40-point scale. The findings suggest that LLM-based grading can provide consistent, scalable assessment of UML diagrams while matching the grading quality of human assessors. This approach offers a promi sing solution for managing growing student numbers while ensuring fair and timely feedback. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 18.216.51.7

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Bouali, N., Gerhold, M., Rehman, T. U. and Ahmed, F. (2025). Toward Automated UML Diagram Assessment: Comparing LLM-Generated Scores with Teaching Assistants. In Proceedings of the 17th International Conference on Computer Supported Education - Volume 1: CSEDU; ISBN 978-989-758-746-7; ISSN 2184-5026, SciTePress, pages 158-169. DOI: 10.5220/0013481900003932

@conference{csedu25,
author={Nacir Bouali and Marcus Gerhold and Tosif Ul Rehman and Faizan Ahmed},
title={Toward Automated UML Diagram Assessment: Comparing LLM-Generated Scores with Teaching Assistants},
booktitle={Proceedings of the 17th International Conference on Computer Supported Education - Volume 1: CSEDU},
year={2025},
pages={158-169},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013481900003932},
isbn={978-989-758-746-7},
issn={2184-5026},
}

TY - CONF

JO - Proceedings of the 17th International Conference on Computer Supported Education - Volume 1: CSEDU
TI - Toward Automated UML Diagram Assessment: Comparing LLM-Generated Scores with Teaching Assistants
SN - 978-989-758-746-7
IS - 2184-5026
AU - Bouali, N.
AU - Gerhold, M.
AU - Rehman, T.
AU - Ahmed, F.
PY - 2025
SP - 158
EP - 169
DO - 10.5220/0013481900003932
PB - SciTePress