Teach AI How to Code: Using Large Language Models as Teachable Agents for Programming Education

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jin, Hyoungwook, Lee, Seonghee, Shin, Hyungyu, Kim, Juho
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929528558845952
author Jin, Hyoungwook
Lee, Seonghee
Shin, Hyungyu
Kim, Juho
author_facet Jin, Hyoungwook
Lee, Seonghee
Shin, Hyungyu
Kim, Juho
contents This work investigates large language models (LLMs) as teachable agents for learning by teaching (LBT). LBT with teachable agents helps learners identify knowledge gaps and discover new knowledge. However, teachable agents require expensive programming of subject-specific knowledge. While LLMs as teachable agents can reduce the cost, LLMs' expansive knowledge as tutees discourages learners from teaching. We propose a prompting pipeline that restrains LLMs' knowledge and makes them initiate "why" and "how" questions for effective knowledge-building. We combined these techniques into TeachYou, an LBT environment for algorithm learning, and AlgoBo, an LLM-based tutee chatbot that can simulate misconceptions and unawareness prescribed in its knowledge state. Our technical evaluation confirmed that our prompting pipeline can effectively configure AlgoBo's problem-solving performance. Through a between-subject study with 40 algorithm novices, we also observed that AlgoBo's questions led to knowledge-dense conversations (effect size=0.71). Lastly, we discuss design implications, cost-efficiency, and personalization of LLM-based teachable agents.
format Preprint
id arxiv_https___arxiv_org_abs_2309_14534
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Teach AI How to Code: Using Large Language Models as Teachable Agents for Programming Education
Jin, Hyoungwook
Lee, Seonghee
Shin, Hyungyu
Kim, Juho
Human-Computer Interaction
This work investigates large language models (LLMs) as teachable agents for learning by teaching (LBT). LBT with teachable agents helps learners identify knowledge gaps and discover new knowledge. However, teachable agents require expensive programming of subject-specific knowledge. While LLMs as teachable agents can reduce the cost, LLMs' expansive knowledge as tutees discourages learners from teaching. We propose a prompting pipeline that restrains LLMs' knowledge and makes them initiate "why" and "how" questions for effective knowledge-building. We combined these techniques into TeachYou, an LBT environment for algorithm learning, and AlgoBo, an LLM-based tutee chatbot that can simulate misconceptions and unawareness prescribed in its knowledge state. Our technical evaluation confirmed that our prompting pipeline can effectively configure AlgoBo's problem-solving performance. Through a between-subject study with 40 algorithm novices, we also observed that AlgoBo's questions led to knowledge-dense conversations (effect size=0.71). Lastly, we discuss design implications, cost-efficiency, and personalization of LLM-based teachable agents.
title Teach AI How to Code: Using Large Language Models as Teachable Agents for Programming Education
topic Human-Computer Interaction
url https://arxiv.org/abs/2309.14534