PLAID: Supporting Computing Instructors to Identify Domain-Specific Programming Plans at Scale

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jain, Yoshee, Demirtaş, Mehmet Arif, Cunningham, Kathryn
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909495613980672
author Jain, Yoshee
Demirtaş, Mehmet Arif
Cunningham, Kathryn
author_facet Jain, Yoshee
Demirtaş, Mehmet Arif
Cunningham, Kathryn
contents Pedagogical approaches focusing on stereotypical code solutions, known as programming plans, can increase problem-solving ability and motivate diverse learners. However, plan-focused pedagogies are rarely used beyond introductory programming. Our formative study (N=10 educators) showed that identifying plans is a tedious process. To advance plan-focused pedagogies in application-focused domains, we created an LLM-powered pipeline that automates the effortful parts of educators' plan identification process by providing use-case-driven program examples and candidate plans. In design workshops (N=7 educators), we identified design goals to maximize instructors' efficiency in plan identification by optimizing interaction with this LLM-generated content. Our resulting tool, PLAID, enables instructors to access a corpus of relevant programs to inspire plan identification, compare code snippets to assist plan refinement, and facilitates them in structuring code snippets into plans. We evaluated PLAID in a within-subjects user study (N=12 educators) and found that PLAID led to lower cognitive demand and increased productivity compared to the state-of-the-art. Educators found PLAID beneficial for generating instructional material. Thus, our findings suggest that human-in-the-loop approaches hold promise for supporting plan-focused pedagogies at scale.
format Preprint
id arxiv_https___arxiv_org_abs_2502_10618
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PLAID: Supporting Computing Instructors to Identify Domain-Specific Programming Plans at Scale
Jain, Yoshee
Demirtaş, Mehmet Arif
Cunningham, Kathryn
Human-Computer Interaction
Pedagogical approaches focusing on stereotypical code solutions, known as programming plans, can increase problem-solving ability and motivate diverse learners. However, plan-focused pedagogies are rarely used beyond introductory programming. Our formative study (N=10 educators) showed that identifying plans is a tedious process. To advance plan-focused pedagogies in application-focused domains, we created an LLM-powered pipeline that automates the effortful parts of educators' plan identification process by providing use-case-driven program examples and candidate plans. In design workshops (N=7 educators), we identified design goals to maximize instructors' efficiency in plan identification by optimizing interaction with this LLM-generated content. Our resulting tool, PLAID, enables instructors to access a corpus of relevant programs to inspire plan identification, compare code snippets to assist plan refinement, and facilitates them in structuring code snippets into plans. We evaluated PLAID in a within-subjects user study (N=12 educators) and found that PLAID led to lower cognitive demand and increased productivity compared to the state-of-the-art. Educators found PLAID beneficial for generating instructional material. Thus, our findings suggest that human-in-the-loop approaches hold promise for supporting plan-focused pedagogies at scale.
title PLAID: Supporting Computing Instructors to Identify Domain-Specific Programming Plans at Scale
topic Human-Computer Interaction
url https://arxiv.org/abs/2502.10618