AI-assisted Automated Short Answer Grading of Handwritten University Level Mathematics Exams
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911998187405312 |
|---|---|
| author | Liu, Tianyi Chatain, Julia Kobel-Keller, Laura Kortemeyer, Gerd Willwacher, Thomas Sachan, Mrinmaya |
| author_facet | Liu, Tianyi Chatain, Julia Kobel-Keller, Laura Kortemeyer, Gerd Willwacher, Thomas Sachan, Mrinmaya |
| contents | Effective and timely feedback in educational assessments is essential but labor-intensive, especially for complex tasks. Recent developments in automated feedback systems, ranging from deterministic response grading to the evaluation of semi-open and open-ended essays, have been facilitated by advances in machine learning. The emergence of pre-trained Large Language Models, such as GPT-4, offers promising new opportunities for efficiently processing diverse response types with minimal customization. This study evaluates the effectiveness of a pre-trained GPT-4 model in grading semi-open handwritten responses in a university-level mathematics exam. Our findings indicate that GPT-4 provides surprisingly reliable and cost-effective initial grading, subject to subsequent human verification. Future research should focus on refining grading rules and enhancing the extraction of handwritten responses to further leverage these technologies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_11728 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | AI-assisted Automated Short Answer Grading of Handwritten University Level Mathematics Exams Liu, Tianyi Chatain, Julia Kobel-Keller, Laura Kortemeyer, Gerd Willwacher, Thomas Sachan, Mrinmaya History and Overview 97-02 Effective and timely feedback in educational assessments is essential but labor-intensive, especially for complex tasks. Recent developments in automated feedback systems, ranging from deterministic response grading to the evaluation of semi-open and open-ended essays, have been facilitated by advances in machine learning. The emergence of pre-trained Large Language Models, such as GPT-4, offers promising new opportunities for efficiently processing diverse response types with minimal customization. This study evaluates the effectiveness of a pre-trained GPT-4 model in grading semi-open handwritten responses in a university-level mathematics exam. Our findings indicate that GPT-4 provides surprisingly reliable and cost-effective initial grading, subject to subsequent human verification. Future research should focus on refining grading rules and enhancing the extraction of handwritten responses to further leverage these technologies. |
| title | AI-assisted Automated Short Answer Grading of Handwritten University Level Mathematics Exams |
| topic | History and Overview 97-02 |
| url | https://arxiv.org/abs/2408.11728 |