"Give me the code" -- Log Analysis of First-Year CS Students' Interactions With GPT
Not on the map. Why?
Abstract (arXiv)
The impact of Large Language Models (LLMs) like GPT-3, GPT-4, and Bard in computer science (CS) education is expected to be profound. Students now have the power to generate code solutions for a wide array of programming assignments. For first-year students, this may be particularly problematic since the foundational skills are still in development and an over-reliance on generative AI tools can hinder their ability to grasp essential programming concepts. This paper analyzes the prompts used by 69 freshmen undergraduate students to solve a certain programming problem within a project assignment, without giving them prior prompt training. We also present the rules of the exercise that motivated the prompts, designed to foster critical thinking skills during the interaction. Despite using unsophisticated prompting techniques, our findings suggest that the majority of students successfully leveraged GPT, incorporating the suggested solutions into their projects. Additionally, half of the students demonstrated the ability to exercise judgment in selecting from multiple GPT-generated solutions, showcasing the development of their critical thinking skills in evaluating AI-generated code.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 20 of its 30 references that are in the map. First posted on arXiv 26 Nov 2024.
Builds on
20 of 30 references.
References · 20
- 2020Language Models are Few-Shot Learnerscited by 32,199
- 2022A Systematic Evaluation of Large Language Models of Codecited by 360
- 2023How is ChatGPT's behavior changing over time?cited by 265
- 2022Conversing with Copilot: Exploring Prompt Engineering for Solving CS1 Problems Using Natural Languagecited by 81
- 2023CodeHelp: Using Large Language Models with Guardrails for Scalable Support in Programming Classescited by 71
- 2023Comparing Code Explanations Created by Students and Large Language Modelscited by 63
- 2023"It's Weird That it Knows What I Want": Usability and Interactions with Copilot for Novice Programmerscited by 62
- 2023How Novices Use LLM-Based Code Generators to Solve CS1 Coding Tasks in a Self-Paced Learning Environmentcited by 55
- 2023Exploring the Responses of Large Language Models to Beginner Programmers' Help Requestscited by 44
- 2023Thrilled by Your Progress! Large Language Models (GPT-4) No Longer Struggle to Pass Assessments in Higher Education Programming Coursescited by 38
- 2023StudentEval: A Benchmark of Student-Written Prompts for Large Language Models of Codecited by 32
- 2023Large Language Models (GPT) Struggle to Answer Multiple-Choice Questions about Codecited by 31
8 more
- 2023Can GPT-4 Support Analysis of Textual Data in Tasks Requiring Highly Specialized Domain Expertise?cited by 30
- 2023Harnessing LLMs in Curricular Design: Using GPT-4 to Support Authoring of Learning Objectivescited by 16
- 2023Promptly: Using Prompt Problems to Teach Learners How to Effectively Utilize AI Code Generatorscited by 16
- 2023ChatGPT, Can You Generate Solutions for my Coding Exercises? An Evaluation on its Effectiveness in an undergraduate Java Programming Coursecited by 12
- 2023A Preliminary Analysis on the Code Generation Capabilities of GPT-3.5 and Bard AI Models for Java Functionscited by 8
- 2024LLMs Still Can't Avoid Instanceof: An Investigation Into GPT-3.5, GPT-4 and Bard's Capacity to Handle Object-Oriented Programming Assignmentscited by 6
- 2023Navigating Complexity in Software Engineering: A Prototype for Comparing GPT-n Solutionscited by 5
- 2023The centaur programmer -- How Kasparov's Advanced Chess spans over to the software development of the futurecited by 3
Built on by
Citing papers per year: 2025: 2.
2 papers.