How Beginning Programmers and Code LLMs (Mis)read Each Other

要旨

Generative AI models, specifically large language models (LLMs), have made strides towards the long-standing goal of text-to-code generation. This progress has invited numerous studies of user interaction. However, less is known about the struggles and strategies of non-experts, for whom each step of the text-to-code problem presents challenges: describing their intent in natural language, evaluating the correctness of generated code, and editing prompts when the generated code is incorrect. This paper presents a large-scale controlled study of how 120 beginning coders across three academic institutions approach writing and editing prompts. A novel experimental design allows us to target specific steps in the text-to-code process and reveals that beginners struggle with writing and editing prompts, even for problems at their skill level and when correctness is automatically determined. Our mixed-methods evaluation provides insight into student processes and perceptions with key implications for non-expert Code LLM use within and outside of education.

著者
Sydney Nguyen
Wellesley College, Wellesley, Massachusetts, United States
Hannah McLean Babe
Oberlin College, Oberlin, Ohio, United States
Yangtian Zi
Northeastern University, Boston, Massachusetts, United States
Arjun Guha
Northeastern University, Boston, Massachusetts, United States
Carolyn Jane. Anderson
Wellesley College, Wellesley, Massachusetts, United States
Molly Q. Feldman
Oberlin College, Oberlin, Ohio, United States
論文URL

https://doi.org/10.1145/3613904.3642706

動画

会議: CHI 2024

The ACM CHI Conference on Human Factors in Computing Systems (https://chi2024.acm.org/)

セッション: Learning Programming with AI

315
4 件の発表
2024-05-15 01:00:00
2024-05-15 02:20:00