Algorithmic Learning: Assessing the Potential of Large Language Models (LLMs) for Automated Exercise Generation and Grading in Educational Settings.
Saved in:
| Title: | Algorithmic Learning: Assessing the Potential of Large Language Models (LLMs) for Automated Exercise Generation and Grading in Educational Settings. |
|---|---|
| Authors: | Zou, Wenlong (AUTHOR), Goh, Tiong-Thye (AUTHOR), Zhu, Huiting (AUTHOR), Liu, Mengjun (AUTHOR), Yang, Bing (AUTHOR) |
| Source: | International Journal of Human-Computer Interaction. Jan2026, Vol. 42 Issue 2, p1206-1223. 18p. |
| Subjects: | ChatGPT, Educational evaluation, Teaching aids, Machine learning, Language models, Ethical problems, Educational technology |
| Abstract: | This study explores ChatGPT's role as a teaching aid in algorithmic education, focusing on its ability to generate and evaluate algorithmic questions and solutions. Qualitative analysis shows strong performance in Sensibleness, Readiness, and Topicality, though Novelty remains an area for improvement. ChatGPT also demonstrated self-improvement in criteria like Efficiency and Robustness, with over 60% enhancement. A comparison of AI and teacher grading revealed that ChatGPT provided accurate assessments, closely aligning with expert evaluations. The findings highlight ChatGPT's potential in educational assessment and call for further exploration of student perceptions and ethical considerations. [ABSTRACT FROM AUTHOR] |
| Copyright of International Journal of Human-Computer Interaction is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Psychology and Behavioral Sciences Collection |
|
Full text is not displayed to guests.
Login for full access.
|
|
| Abstract: | This study explores ChatGPT's role as a teaching aid in algorithmic education, focusing on its ability to generate and evaluate algorithmic questions and solutions. Qualitative analysis shows strong performance in Sensibleness, Readiness, and Topicality, though Novelty remains an area for improvement. ChatGPT also demonstrated self-improvement in criteria like Efficiency and Robustness, with over 60% enhancement. A comparison of AI and teacher grading revealed that ChatGPT provided accurate assessments, closely aligning with expert evaluations. The findings highlight ChatGPT's potential in educational assessment and call for further exploration of student perceptions and ethical considerations. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 10447318 |
| DOI: | 10.1080/10447318.2025.2520931 |
