Automatic Large Language Models Creation of Interactive Learning Lessons
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909654563422208 |
|---|---|
| author | Lin, Jionghao Rao, Jiarui Zhao, Yiyang Wang, Yuting Gurung, Ashish Barany, Amanda Ocumpaugh, Jaclyn Baker, Ryan S. Koedinger, Kenneth R. |
| author_facet | Lin, Jionghao Rao, Jiarui Zhao, Yiyang Wang, Yuting Gurung, Ashish Barany, Amanda Ocumpaugh, Jaclyn Baker, Ryan S. Koedinger, Kenneth R. |
| contents | We explore the automatic generation of interactive, scenario-based lessons designed to train novice human tutors who teach middle school mathematics online. Employing prompt engineering through a Retrieval-Augmented Generation approach with GPT-4o, we developed a system capable of creating structured tutor training lessons. Our study generated lessons in English for three key topics: Encouraging Students' Independence, Encouraging Help-Seeking Behavior, and Turning on Cameras, using a task decomposition prompting strategy that breaks lesson generation into sub-tasks. The generated lessons were evaluated by two human evaluators, who provided both quantitative and qualitative evaluations using a comprehensive rubric informed by lesson design research. Results demonstrate that the task decomposition strategy led to higher-rated lessons compared to single-step generation. Human evaluators identified several strengths in the LLM-generated lessons, including well-structured content and time-saving potential, while also noting limitations such as generic feedback and a lack of clarity in some instructional sections. These findings underscore the potential of hybrid human-AI approaches for generating effective lessons in tutor training. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_17356 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Automatic Large Language Models Creation of Interactive Learning Lessons Lin, Jionghao Rao, Jiarui Zhao, Yiyang Wang, Yuting Gurung, Ashish Barany, Amanda Ocumpaugh, Jaclyn Baker, Ryan S. Koedinger, Kenneth R. Computers and Society Artificial Intelligence Human-Computer Interaction We explore the automatic generation of interactive, scenario-based lessons designed to train novice human tutors who teach middle school mathematics online. Employing prompt engineering through a Retrieval-Augmented Generation approach with GPT-4o, we developed a system capable of creating structured tutor training lessons. Our study generated lessons in English for three key topics: Encouraging Students' Independence, Encouraging Help-Seeking Behavior, and Turning on Cameras, using a task decomposition prompting strategy that breaks lesson generation into sub-tasks. The generated lessons were evaluated by two human evaluators, who provided both quantitative and qualitative evaluations using a comprehensive rubric informed by lesson design research. Results demonstrate that the task decomposition strategy led to higher-rated lessons compared to single-step generation. Human evaluators identified several strengths in the LLM-generated lessons, including well-structured content and time-saving potential, while also noting limitations such as generic feedback and a lack of clarity in some instructional sections. These findings underscore the potential of hybrid human-AI approaches for generating effective lessons in tutor training. |
| title | Automatic Large Language Models Creation of Interactive Learning Lessons |
| topic | Computers and Society Artificial Intelligence Human-Computer Interaction |
| url | https://arxiv.org/abs/2506.17356 |