Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
The Use of Generative AI Tools in Assessing Openended Text-based Examinations
Higher Colleges of Technology, United Arab Emirates (UAE) .
NSBM Green University, Sri Lanka .
Stockholm University, Faculty of Social Sciences, Department of Computer and Systems Sciences.ORCID iD: 0000-0003-1153-1870
Number of Authors: 32025 (English)In: 2025 10th International Conference on Information Technology Trends (ITT), Piscataway: IEEE, 2025, p. 147-151Conference paper, Published paper (Refereed)
Abstract [en]

With the increasing demand and enrollment of students in higher education, academics must spend significant time providing feedback and evaluations. This study attempts to study the use of generative artificial intelligence (GenAI) tools in assessment. The primary aim is to examine how effective GenAI tools are in evaluating, especially for open-ended short text-based questions. A case study was conducted using students who follow a foundation program in computing at a leading university in Sri Lanka. A proctored online examination was set up in a controlled environment, and answers were evaluated using ChatGPT, Gemini, and manual methods. The evaluation was carried out using common rubrics in all three methods mentioned above, and the marks generated and given were compared using all three evaluation methods. Interestingly, the results show that compared to ChatGPT and Gemini, the evaluation results are much closer to the marks manually given by using manual marking. The ChatGPT and Gemini as GenAI tools generated answers that are also closer to each other. The findings prove that we can use GenAI tools effectively to evaluate structured examinations and provide results based on pre-defined rubrics. This will reduce the significant time taken for the evaluation and improve the productivity of academics.

Place, publisher, year, edition, pages
Piscataway: IEEE, 2025. p. 147-151
Keywords [en]
AI-based Evaluation, GenAI tools, Online Examinations, Open-ended Questions
National Category
Artificial Intelligence Educational Work
Identifiers
URN: urn:nbn:se:su:diva-254767DOI: 10.1109/ITT69610.2025.11352898Scopus ID: 2-s2.0-105033661581ISBN: 979-8-3315-4575-8 (electronic)ISBN: 979-8-3315-4576-5 (print)OAI: oai:DiVA.org:su-254767DiVA, id: diva2:2056535
Conference
10th International Conference on Information Technology Trends (ITT 2025), Dubai, United Arab Emirates, 6–7 November, 2025
Available from: 2026-04-29 Created: 2026-04-29 Last updated: 2026-04-29Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Hansson, Henrik

Search in DiVA

By author/editor
Hansson, Henrik
By organisation
Department of Computer and Systems Sciences
Artificial IntelligenceEducational Work

Search outside of DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 28 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf