How to Teach Programming in the AI Era? Using LLMs as a Teachable Agent for Debugging

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ma, Qianou, Shen, Hua, Koedinger, Kenneth, Wu, Tongshuang
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909343664832512
author Ma, Qianou
Shen, Hua
Koedinger, Kenneth
Wu, Tongshuang
author_facet Ma, Qianou
Shen, Hua
Koedinger, Kenneth
Wu, Tongshuang
contents Large Language Models (LLMs) now excel at generative skills and can create content at impeccable speeds. However, they are imperfect and still make various mistakes. In a Computer Science education context, as these models are widely recognized as "AI pair programmers," it becomes increasingly important to train students on evaluating and debugging the LLM-generated code. In this work, we introduce HypoCompass, a novel system to facilitate deliberate practice on debugging, where human novices play the role of Teaching Assistants and help LLM-powered teachable agents debug code. We enable effective task delegation between students and LLMs in this learning-by-teaching environment: students focus on hypothesizing the cause of code errors, while adjacent skills like code completion are offloaded to LLM-agents. Our evaluations demonstrate that HypoCompass generates high-quality training materials (e.g., bugs and fixes), outperforming human counterparts fourfold in efficiency, and significantly improves student performance on debugging by 12% in the pre-to-post test.
format Preprint
id arxiv_https___arxiv_org_abs_2310_05292
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle How to Teach Programming in the AI Era? Using LLMs as a Teachable Agent for Debugging
Ma, Qianou
Shen, Hua
Koedinger, Kenneth
Wu, Tongshuang
Human-Computer Interaction
Software Engineering
Large Language Models (LLMs) now excel at generative skills and can create content at impeccable speeds. However, they are imperfect and still make various mistakes. In a Computer Science education context, as these models are widely recognized as "AI pair programmers," it becomes increasingly important to train students on evaluating and debugging the LLM-generated code. In this work, we introduce HypoCompass, a novel system to facilitate deliberate practice on debugging, where human novices play the role of Teaching Assistants and help LLM-powered teachable agents debug code. We enable effective task delegation between students and LLMs in this learning-by-teaching environment: students focus on hypothesizing the cause of code errors, while adjacent skills like code completion are offloaded to LLM-agents. Our evaluations demonstrate that HypoCompass generates high-quality training materials (e.g., bugs and fixes), outperforming human counterparts fourfold in efficiency, and significantly improves student performance on debugging by 12% in the pre-to-post test.
title How to Teach Programming in the AI Era? Using LLMs as a Teachable Agent for Debugging
topic Human-Computer Interaction
Software Engineering
url https://arxiv.org/abs/2310.05292