arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2404.19397cs.HCcs.LG
收藏

人类能教会机器编程吗?

Can humans teach machines to code?

University of Southampton(南安普顿大学);University of Bamberg(班贝格大学);University of Oxford(牛津大学)

Céline Hocquette, Johannes Langer, Andrew Cropper, Ute Schmid

AI总结:

本文通过让人类为六个编程概念提供示例,并比较五个程序综合系统在非专家、专家和随机示例上的泛化表现,发现非专家通常难以提供足以让系统学会准确程序的示例。

摘要:

归纳式程序综合的目标是让机器根据用户提供的示例自动生成程序。其背后的一个关键假设是,人类能够提供足够的示例,将某个概念教给机器。为评估该假设的有效性,我们开展了一项研究:让人类参与者为六个编程概念提供示例,例如查找列表中的最大元素。我们评估了五个程序综合系统在三类输入-输出示例上训练后的泛化性能:(i)来自非专家人类的示例,(ii)来自人类专家的示例,以及(iii)随机采样的示例。结果表明,非专家通常无法提供足够的示例,使程序综合系统学习到准确的程序。

英文摘要:

The goal of inductive program synthesis is for a machine to automatically generate a program from user-supplied examples. A key underlying assumption is that humans can provide sufficient examples to teach a concept to a machine. To evaluate the validity of this assumption, we conduct a study where human participants provide examples for six programming concepts, such as finding the maximum element of a list. We evaluate the generalisation performance of five program synthesis systems trained on input-output examples (i) from non-expert humans, (ii) from a human expert, and (iii) randomly sampled. Our results suggest that non-experts typically do not provide sufficient examples for a program synthesis system to learn an accurate program.

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。

↑