Automatic Large Language Models Creation of Interactive Learning Lessons

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lin, Jionghao, Rao, Jiarui, Zhao, Yiyang, Wang, Yuting, Gurung, Ashish, Barany, Amanda, Ocumpaugh, Jaclyn, Baker, Ryan S., Koedinger, Kenneth R.
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