Exploring How Multiple Levels of GPT-Generated Programming Hints Support or Disappoint Novices

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xiao, Ruiwei, Hou, Xinying, Stamper, John
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914739147243520
author Xiao, Ruiwei
Hou, Xinying
Stamper, John
author_facet Xiao, Ruiwei
Hou, Xinying
Stamper, John
contents Recent studies have integrated large language models (LLMs) into diverse educational contexts, including providing adaptive programming hints, a type of feedback focuses on helping students move forward during problem-solving. However, most existing LLM-based hint systems are limited to one single hint type. To investigate whether and how different levels of hints can support students' problem-solving and learning, we conducted a think-aloud study with 12 novices using the LLM Hint Factory, a system providing four levels of hints from general natural language guidance to concrete code assistance, varying in format and granularity. We discovered that high-level natural language hints alone can be helpless or even misleading, especially when addressing next-step or syntax-related help requests. Adding lower-level hints, like code examples with in-line comments, can better support students. The findings open up future work on customizing help responses from content, format, and granularity levels to accurately identify and meet students' learning needs.
format Preprint
id arxiv_https___arxiv_org_abs_2404_02213
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Exploring How Multiple Levels of GPT-Generated Programming Hints Support or Disappoint Novices
Xiao, Ruiwei
Hou, Xinying
Stamper, John
Human-Computer Interaction
Artificial Intelligence
Computers and Society
Recent studies have integrated large language models (LLMs) into diverse educational contexts, including providing adaptive programming hints, a type of feedback focuses on helping students move forward during problem-solving. However, most existing LLM-based hint systems are limited to one single hint type. To investigate whether and how different levels of hints can support students' problem-solving and learning, we conducted a think-aloud study with 12 novices using the LLM Hint Factory, a system providing four levels of hints from general natural language guidance to concrete code assistance, varying in format and granularity. We discovered that high-level natural language hints alone can be helpless or even misleading, especially when addressing next-step or syntax-related help requests. Adding lower-level hints, like code examples with in-line comments, can better support students. The findings open up future work on customizing help responses from content, format, and granularity levels to accurately identify and meet students' learning needs.
title Exploring How Multiple Levels of GPT-Generated Programming Hints Support or Disappoint Novices
topic Human-Computer Interaction
Artificial Intelligence
Computers and Society
url https://arxiv.org/abs/2404.02213