Large Language Models in Introductory Programming Education: ChatGPT's Performance and Implications for Assessments

Dominic Lohr H. Keuning Natalie Kiesler

31 Agustus 2023

Ever since the emergence of large language models (LLMs) and related applications, such as ChatGPT, its performance and error analysis for programming tasks have been subject to research. In this work-in-progress paper, we explore the potential of such LLMs for computing educators and learners, as we analyze the feedback it generates to a given input containing program code. In particular, we aim at (1) exploring how an LLM like ChatGPT responds to students seeking help with their introductory programming tasks, and (2) identifying feedback types in its responses. To achieve these goals, we used students' programming sequences from a dataset gathered within a CS1 course as input for ChatGPT along with questions required to elicit feedback and correct solutions. The results show that ChatGPT performs reasonably well for some of the introductory programming tasks and student errors, which means that students can potentially benefit. However, educators should provide guidance on how to use the provided feedback, as it can contain misleading information for novices.

M. Sakr Marshall An C. Bogart + 2 lainnya

15 Juni 2023

This paper studies recent developments in large language models’ (LLM) abilities to pass assessments in introductory and intermediate Python programming courses at the postsecondary level. The emergence of ChatGPT resulted in heated debates of its potential uses (e.g., exercise generation, code explanation) as well as misuses in programming classes (e.g., cheating). Recent studies show that while the technology performs surprisingly well on diverse sets of assessment instruments employed in typical programming classes the performance is usually not sufficient to pass the courses. The release of GPT-4 largely emphasized notable improvements in the capabilities related to handling assessments originally designed for human test-takers. This study is the necessary analysis in the context of this ongoing transition towards mature generative AI systems. Specifically, we report the performance of GPT-4, comparing it to the previous generations of GPT models, on three Python courses with assessments ranging from simple multiple-choice questions (no code involved) to complex programming projects with code bases distributed into multiple files (599 exercises overall). Additionally, we analyze the assessments that were not handled well by GPT-4 to understand the current limitations of the model, as well as its capabilities to leverage feedback provided by an auto-grader. We found that the GPT models evolved from completely failing the typical programming class’ assessments (the original GPT-3) to confidently passing the courses with no human involvement (GPT-4). While we identified certain limitations in GPT-4’s handling of MCQs and coding exercises, the rate of improvement across the recent generations of GPT models strongly suggests their potential to handle almost any type of assessment widely used in higher education programming courses. These findings could be leveraged by educators and institutions to adapt the design of programming assessments as well as to fuel the necessary discussions into how programming classes should be updated to reflect the recent technological developments. This study provides evidence that programming instructors need to prepare for a world in which there is an easy-to-use widely accessible technology that can be utilized by learners to collect passing scores, with no effort whatsoever, on what today counts as viable programming knowledge and skills assessments.

Kevin Ly Mollie Jordan Adalbert Gerald Soosai Raj

7 Maret 2024

Large language models (LLMs) like ChatGPT are changing computing education and may create additional barriers to those already faced by non-native English speakers (NNES) learning computing. We investigate an opportunity for a positive impact of LLMs on NNES through multilingual programming exercise generation. Following previous work with LLM exercise generation in English, we prompt OpenAI GPT-3.5 in 4 natural languages (English, Tamil, Spanish, and Vietnamese) to create introductory programming problems, sample solutions, and test cases. We evaluate these problems on their sensibility, readability, translation, sample solution accuracy, topicality, and cultural relevance. We find that problems generated in English, Spanish, and Vietnamese are largely sensible, easily understood, and accurate in their sample solutions. However, Tamil problems are mostly non-sensible and have a much lower passing test rate, indicating that the abilities of LLMs for problem generation are not generalizable across languages. Our analysis suggests that these problems could not be given verbatim to students, but with minimal effort, most errors can be fixed. We further discuss the benefits of these problems despite their flaws, and their opportunities to provide personalized and culturally relevant resources for students in their native languages.

Cemal Yilmaz Orçun Çetin Khadija Hanifi

22 Oktober 2023

ChatGPT, an increasingly popular Large Language Model (LLM), has found widespread acceptance, especially among the younger generation, who rely on it for various tasks, such as comprehending complex course materials and tackling homework assignments. This surge in interest has drawn the attention of researchers, leading to numerous studies that delve into the advantages and disadvantages of the upcoming LLM dominant era. In our research, we explore the influence of ChatGPT and similar models on the field of software engineering, specifically from the perspective of software engineering students. Our main objective is to gain valuable insights into their usage habits and opinions through a comprehensive survey. The survey encompassed diverse questions, addressing the specific areas where ChatGPT was utilized for assistance and gathering students’ reflections on each aspect. We found that ChatGPT has garnered widespread acceptance among software engineering students, with 93% of them utilizing it for their projects. These students expressed satisfaction with the level of assistance provided, and most intend to continue using it as a valuable tool in their work. During our investigation, we also assessed the students’ awareness of the underlying technologies behind ChatGPT. Approximately half of the students demonstrated awareness of these technologies, while 38.7% had made extra efforts to explore prompt engineering to enhance ChatGPT’s productivity. However, an important finding was that 90.6% of the students reported experiencing hallucinations during their interactions with ChatGPT. These hallucinations were shared as examples, raising significant concerns that warrant further exploration and mitigation. Moreover, we delved into potential improvements and gathered valuable recommendations, which could help ChatGPT to become even more effective and dependable in its applications.

Paul Denny Juho Leinonen Arto Hellas + 1 lainnya

3 Juni 2022

This article explores the natural language generation capabilities of large language models with application to the production of two types of learning resources common in programming courses. Using OpenAI Codex as the large language model, we create programming exercises (including sample solutions and test cases) and code explanations, assessing these qualitatively and quantitatively. Our results suggest that the majority of the automatically generated content is both novel and sensible, and in some cases ready to use as is. When creating exercises we find that it is remarkably easy to influence both the programming concepts and the contextual themes they contain, simply by supplying keywords as input to the model. Our analysis suggests that there is significant value in massive generative machine learning models as a tool for instructors, although there remains a need for some oversight to ensure the quality of the generated content before it is delivered to students. We further discuss the implications of OpenAI Codex and similar tools for introductory programming education and highlight future research streams that have the potential to improve the quality of the educational experience for both teachers and students alike.