Leveraging LLMs for Assignment Report Summaries to Support Teacher Insights in Intelligent Tutoring Systems
Saved in:
| Title: | Leveraging LLMs for Assignment Report Summaries to Support Teacher Insights in Intelligent Tutoring Systems |
|---|---|
| Language: | English |
| Authors: | Wen-Chiang Ivan Lim, Neil T. Heffernan III, Ivan Eroshenko, Wai Khumwang, Pei-Chen Chan |
| Source: | Grantee Submission. 2025. |
| Peer Reviewed: | Y |
| Page Count: | 5 |
| Publication Date: | 2025 |
| Sponsoring Agency: | National Science Foundation (NSF) Department of Education (ED) Office of Naval Research (ONR) (DOD) National Institutes of Health (NIH) (DHHS) Institute of Education Sciences (ED) |
| Contract Number: | 2118725 2118904 |
| Document Type: | Speeches/Meeting Papers Reports - Research |
| Descriptors: | Intelligent Tutoring Systems, Natural Language Processing, Assignments, Learning Management Systems, Reports, Tables (Data), Documentation, Learning Analytics, Data Use, Data Processing |
| DOI: | 10.1145/3698205.3733955 |
| Abstract: | Intelligent tutoring systems are increasingly used in schools, providing teachers with valuable analytics on student learning. However, many teachers lack the time to review these reports in detail due to heavy workloads, and some face challenges with data literacy. This project investigates the use of large language models (LLMs) to generate brief, actionable summaries of assignment reports, making key insights more accessible. We evaluated different solutions to tabular data summarization, including direct text conversion, sentence serialization, and rule-based aggregation approaches. Our findings suggest that sentence serialization is currently the most viable approach, offering informative summaries with moderate token usage. Future work will focus on refining these methods, exploring teachers' perceived utility of a summary, and assessing the impact on teachers' engagement. Code and data are available at: https://osf.io/yzts6/files/osfstorage?view_only=d5bd7f557d8843da8 fa3a6b52e3822fe. [This paper was published in: "Proceedings of the Twelfth ACM Conference on Learning @ Scale (L@S '25), July 21-23, 2025, Palermo, Italy," ACM, 2025, pp. 356-360.] |
| Abstractor: | As Provided |
| Notes: | https://osf.io/yzts6/files/osfstorage?view_only=d5bd7f557d8843da8fa3a6b52e3822fe |
| IES Funded: | Yes |
| Entry Date: | 2025 |
| Accession Number: | ED677067 |
| Database: | ERIC |
| Abstract: | Intelligent tutoring systems are increasingly used in schools, providing teachers with valuable analytics on student learning. However, many teachers lack the time to review these reports in detail due to heavy workloads, and some face challenges with data literacy. This project investigates the use of large language models (LLMs) to generate brief, actionable summaries of assignment reports, making key insights more accessible. We evaluated different solutions to tabular data summarization, including direct text conversion, sentence serialization, and rule-based aggregation approaches. Our findings suggest that sentence serialization is currently the most viable approach, offering informative summaries with moderate token usage. Future work will focus on refining these methods, exploring teachers' perceived utility of a summary, and assessing the impact on teachers' engagement. Code and data are available at: https://osf.io/yzts6/files/osfstorage?view_only=d5bd7f557d8843da8 fa3a6b52e3822fe. [This paper was published in: "Proceedings of the Twelfth ACM Conference on Learning @ Scale (L@S '25), July 21-23, 2025, Palermo, Italy," ACM, 2025, pp. 356-360.] |
|---|---|
| DOI: | 10.1145/3698205.3733955 |
