arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2410.08922cs.HCcs.AI
收藏

探索增强学习的AI生成代码认知参与技术的设计空间

Exploring the Design Space of Cognitive Engagement Techniques with AI-Generated Code for Enhanced Learning

University of Toronto(多伦多大学);Carnegie Mellon University(卡内基梅隆大学)

Majeed Kazemitabaar, Oliver Huang, Sangho Suh, Austin Z. Henley, Tovi Grossman

AI总结:

针对新手依赖LLM生成代码导致浅层学习的问题,本文开发并评估了七种认知参与技术,发现引导学习者通过交互式对话逐步解决问题最为有效。

摘要:

新手程序员越来越依赖大型语言模型(LLMs)来生成代码,以学习编程概念。然而,这种交互可能导致浅层参与,给学习者造成学习的错觉并阻碍技能发展。为解决这一问题,我们进行了系统性的设计探索,开发了七种认知参与技术,旨在促进学习者对AI生成代码的深度参与。本文描述了我们的设计过程、最初的七种技术以及一项被试间研究(N=82)的结果。随后,我们迭代地优化了排名靠前的技术,并通过一项被试内研究(N=42)进一步评估了它们。我们评估了每种技术引入的摩擦力、它们在帮助学习者无AI协助下将概念应用于同构任务的有效性,以及它们在使学习者感知编码能力与实际能力相一致方面的成功度。最终,结果突显了最有效的技术:引导学习者逐步完成问题解决过程,在此过程中他们与AI进行交互式对话,在揭示相应代码之前提示每个阶段需要做什么。

英文摘要:

Novice programmers are increasingly relying on Large Language Models (LLMs) to generate code for learning programming concepts. However, this interaction can lead to superficial engagement, giving learners an illusion of learning and hindering skill development. To address this issue, we conducted a systematic design exploration to develop seven cognitive engagement techniques aimed at promoting deeper engagement with AI-generated code. In this paper, we describe our design process, the initial seven techniques and results from a between-subjects study (N=82). We then iteratively refined the top techniques and further evaluated them through a within-subjects study (N=42). We evaluate the friction each technique introduces, their effectiveness in helping learners apply concepts to isomorphic tasks without AI assistance, and their success in aligning learners' perceived and actual coding abilities. Ultimately, our results highlight the most effective technique: guiding learners through the step-by-step problem-solving process, where they engage in an interactive dialog with the AI, prompting what needs to be done at each stage before the corresponding code is revealed.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑