Can humans teach machines to code?

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hocquette, Céline, Langer, Johannes, Cropper, Andrew, Schmid, Ute
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915153371463680
author Hocquette, Céline
Langer, Johannes
Cropper, Andrew
Schmid, Ute
author_facet Hocquette, Céline
Langer, Johannes
Cropper, Andrew
Schmid, Ute
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2404_19397
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Can humans teach machines to code?
Hocquette, Céline
Langer, Johannes
Cropper, Andrew
Schmid, Ute
Human-Computer Interaction
Machine Learning
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.
title Can humans teach machines to code?
topic Human-Computer Interaction
Machine Learning
url https://arxiv.org/abs/2404.19397