Let's Ask AI About Their Programs : Exploring ChatGPT's Answers To Program Comprehension Questions

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

7 Downloads (Pure)

Abstract

Recent research has explored the creation of questions from code submitted by students. These Questions about Learners' Code (QLCs) are created through program analysis, exploring execution paths, and then creating code comprehension questions from these paths and the broader code structure. Responding to the questions requires reading and tracing the code, which is known to support students' learning. At the same time, computing education researchers have witnessed the emergence of Large Language Models (LLMs) that have taken the community by storm. Researchers have demonstrated the applicability of these models especially in the introductory programming context, outlining their performance in solving introductory programming problems and their utility in creating new learning resources. In this work, we explore the capability of the state-of-the-art LLMs (GPT-3.5 and GPT-4) in answering QLCs that are generated from code that the LLMs have created. Our results show that although the state-of-the-art LLMs can create programs and trace program execution when prompted, they easily succumb to similar errors that have previously been recorded for novice programmers. These results demonstrate the fallibility of these models and perhaps dampen the expectations fueled by the recent LLM hype. At the same time, we also highlight future research possibilities such as using LLMs to mimic students as their behavior can indeed be similar for some specific tasks.
Original languageEnglish
Title of host publicationProceedings of the 46th International Conference on Software Engineering: Software Engineering Education and Training
PublisherACM
Pages221-232
Number of pages12
ISBN (Electronic)979-8-4007-0498-7
DOIs
Publication statusPublished - 24 May 2024
MoE publication typeA4 Conference publication
EventInternational Conference on Software Engineering - Centro Cultural de Bélem, Lisbon, Portugal
Duration: 14 Apr 202420 Apr 2024
Conference number: 46

Conference

ConferenceInternational Conference on Software Engineering
Abbreviated titleICSE-SEET
Country/TerritoryPortugal
CityLisbon
Period14/04/202420/04/2024

Keywords

  • QLCs
  • artificial intellegence
  • introductory programming
  • large language models
  • program comprehension

Fingerprint

Dive into the research topics of 'Let's Ask AI About Their Programs : Exploring ChatGPT's Answers To Program Comprehension Questions'. Together they form a unique fingerprint.

Cite this