Use of AI-driven Code Generation Models in Teaching and Learning Programming: a Systematic Literature Review
OnlineGlobalIn-Person
The recent emergence of LLM-based code generation models can potentially transform programming education. To pinpoint the current state of research on using LLM-based code generators to support the teaching and learning of programming, we conducted a systematic literature review of 21 papers published since 2018. The review focuses on (1) the teaching and learning practices in programming education that utilized LLM-based code generation models, (2) characteristics and (3) performance indicators of the models, and (4) aspects to consider when utilizing the models in programming education, including the risks and challenges. We found that the most commonly reported uses of LLM-based code generation models for teachers are generating assignments and evaluating student work, while for students, the models function as virtual tutors. We identified that the models exhibit accuracy limitations; generated content often contains minor errors that are manageable by instructors but pose risks for novice learners. Moreover, risks such as academic misconduct and over-reliance on the models are critical when considering integrating these models into education. Overall, LLM-based code generation models can be an assistive tool for both learners and instructors if the risks are mitigated.
Fri 22 MarDisplayed time zone: Pacific Time (US & Canada) change
10:45 - 12:00 | Generative AIPapers at Meeting Room E146 Chair(s): Andreas Stefik University of Nevada at Las Vegas, USA | ||
10:45 25mTalk | Use of AI-driven Code Generation Models in Teaching and Learning Programming: a Systematic Literature Review Papers DOI | ||
11:10 25mTalk | Exploring the Impact of Generative AI for StandUp Report Recommendations in Software Capstone Project DevelopmentOnlineIn-Person Papers Andres Neyem Computer Science Department, Pontificia Universidad Catolica de Chile, Juan Pablo Sandoval Computer Science Department, Pontificia Universidad Catolica de Chile, Marcelo Mendoza Computer Science Department, Pontificia Universidad Catolica de Chile, Leonardo Centellas Computer Science Department, Pontificia Universidad Catolica de Chile, Luis Armando Gonzalez Pontificia Universidad Católica de Chile, Carlos Paredes Computer Science Department, Pontificia Universidad Catolica de Chile DOI | ||
11:35 25mTalk | ChatGPT in the Classroom: An Analysis of Its Strengths and Weaknesses for Solving Undergraduate Computer Science QuestionsOnlineIn-Person Papers Ishika Joshi Indraprastha Institute of Information Technology, Delhi, Ritvik Budhiraja Indraprastha Institute of Information Technology, Delhi, Harshal Dev Indraprastha Institute of Information Technology, Delhi, Jahnvi Kadia Indraprastha Institute of Information Technology, Delhi, M. Osama Ataullah Indraprastha Institute of Information Technology, Delhi, Sayan Mitra Indraprastha Institute of Information Technology, Delhi, Harshal D. Akolekar Indian Institute of Technology, Jodhpur, Dhruv Kumar Indraprastha Institute of Information Technology, Delhi DOI |