# Schemex: Discovering Structural Abstractions from Examples

Source: [Schemex: Discovering Structural Abstractions from Examples](<https://www.sota2.com/research/paper/68fa7b691e209131cea8841d>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-11T05:00:04.810Z

Authors: Sitong Wang, Samia Menon, Dingzeyu Li, Xiaojuan Ma, Richard Zemel, Lydia B. Chilton

Published: 2025-04-16T06:02:31.000Z

## Abstract

Creative and communicative work is often underpinned by implicit structures, such as the Hero's Journey in storytelling, design patterns in software, or chord progressions in music. People often learn these structures from examples - a process known as schema induction. However, because schemas are abstract and implicit, they are difficult to discover: shared structural patterns are obscured by surface-level variation, and balancing generality with specificity is challenging. We present Schemex, an interactive AI workflow that systematically supports schema induction by decomposing it into three tractable stages: clustering examples, abstracting candidate schemas, and contrastively refining them by generating new instances and comparing against originals. Studies show that Schemex produces more actionable schemas than a frontier baseline without sacrificing generalizability, with participants uncovering deep and nuanced structural patterns. We also discuss design implications for the cognitive role of interactive process in structure discovery.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Schema Generation Quality Evaluation on Technical Evaluation Test Suite (6 domains)](<https://www.sota2.com/research/sota/schema-generation-quality-evaluation-on-technical-evaluation-test-suite-6-domains.md>): Schema Generation Quality Evaluation; Technical Evaluation Test Suite 6 domain topics: job talk abstracts, teaser videos, LinkedIn summaries, pitch decks, news headlines, news TikToks; Schema Granularity: 6.8.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2504.11795>)

[PDF](<https://arxiv.org/pdf/2504.11795.pdf>)
