Schemex: Discovering Design Patterns from Examples through Iterative Abstraction and Refinement

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Sitong, Chilton, Lydia B.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912239986933760
author Wang, Sitong
Chilton, Lydia B.
author_facet Wang, Sitong
Chilton, Lydia B.
contents Expertise is often built by learning from examples. This process, known as schema induction, helps us identify patterns from examples. Despite its importance, schema induction remains a challenging cognitive task. Recent advances in generative AI reasoning capabilities offer new opportunities to support schema induction through human-AI collaboration. We present Schemex, an AI-powered workflow that enhances human schema induction through three stages: clustering, abstraction, and refinement via contrasting examples. We conducted an initial evaluation of Schemex through two real-world case studies: writing abstracts for HCI papers and creating news TikToks. Qualitative analysis demonstrates the high accuracy and usefulness of the generated schemas. We also discuss future work on developing more flexible methods for workflow construction to help humans focus on high-level thinking.
format Preprint
id arxiv_https___arxiv_org_abs_2502_15105
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Schemex: Discovering Design Patterns from Examples through Iterative Abstraction and Refinement
Wang, Sitong
Chilton, Lydia B.
Human-Computer Interaction
Expertise is often built by learning from examples. This process, known as schema induction, helps us identify patterns from examples. Despite its importance, schema induction remains a challenging cognitive task. Recent advances in generative AI reasoning capabilities offer new opportunities to support schema induction through human-AI collaboration. We present Schemex, an AI-powered workflow that enhances human schema induction through three stages: clustering, abstraction, and refinement via contrasting examples. We conducted an initial evaluation of Schemex through two real-world case studies: writing abstracts for HCI papers and creating news TikToks. Qualitative analysis demonstrates the high accuracy and usefulness of the generated schemas. We also discuss future work on developing more flexible methods for workflow construction to help humans focus on high-level thinking.
title Schemex: Discovering Design Patterns from Examples through Iterative Abstraction and Refinement
topic Human-Computer Interaction
url https://arxiv.org/abs/2502.15105