Research

Paper

AI LLM February 25, 2026

Codesigning Ripplet: an LLM-Assisted Assessment Authoring System Grounded in a Conceptual Model of Teachers' Workflows

Authors

Yuan Cui, Annabel Goldman, Jovy Zhou, Xiaolin Liu, Clarissa Shieh, Joshua Yao, Mia Cheng, Matthew Kay, Fumeng Yang

Abstract

Assessments are critical in education, but creating them can be difficult. To address this challenge in a grounded way, we partnered with 13 teachers in a seven-month codesign process. We developed a conceptual model that characterizes the iterative dual process where teachers develop assessments while simultaneously refining requirements. To enact this model in practice, we built Ripplet, a web-based tool with multilevel reusable interactions to support assessment authoring. The extended codesign revealed that Ripplet enabled teachers to create formative assessments they would not have otherwise made, shifted their practices from generation to curation, and helped them reflect more on assessment quality. In a user study with 15 additional teachers, compared to their current practices, teachers felt the results were more worth their effort and that assessment quality improved.

Metadata

arXiv ID: 2602.22186
Provider: ARXIV
Primary Category: cs.HC
Published: 2026-02-25
Fetched: 2026-02-26 05:00

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.22186v1</id>\n    <title>Codesigning Ripplet: an LLM-Assisted Assessment Authoring System Grounded in a Conceptual Model of Teachers' Workflows</title>\n    <updated>2026-02-25T18:30:44Z</updated>\n    <link href='https://arxiv.org/abs/2602.22186v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.22186v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Assessments are critical in education, but creating them can be difficult. To address this challenge in a grounded way, we partnered with 13 teachers in a seven-month codesign process. We developed a conceptual model that characterizes the iterative dual process where teachers develop assessments while simultaneously refining requirements. To enact this model in practice, we built Ripplet, a web-based tool with multilevel reusable interactions to support assessment authoring. The extended codesign revealed that Ripplet enabled teachers to create formative assessments they would not have otherwise made, shifted their practices from generation to curation, and helped them reflect more on assessment quality. In a user study with 15 additional teachers, compared to their current practices, teachers felt the results were more worth their effort and that assessment quality improved.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.HC'/>\n    <published>2026-02-25T18:30:44Z</published>\n    <arxiv:comment>Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems</arxiv:comment>\n    <arxiv:primary_category term='cs.HC'/>\n    <author>\n      <name>Yuan Cui</name>\n    </author>\n    <author>\n      <name>Annabel Goldman</name>\n    </author>\n    <author>\n      <name>Jovy Zhou</name>\n    </author>\n    <author>\n      <name>Xiaolin Liu</name>\n    </author>\n    <author>\n      <name>Clarissa Shieh</name>\n    </author>\n    <author>\n      <name>Joshua Yao</name>\n    </author>\n    <author>\n      <name>Mia Cheng</name>\n    </author>\n    <author>\n      <name>Matthew Kay</name>\n    </author>\n    <author>\n      <name>Fumeng Yang</name>\n    </author>\n    <arxiv:doi>10.1145/3772318.3790418</arxiv:doi>\n    <link href='https://doi.org/10.1145/3772318.3790418' rel='related' title='doi'/>\n  </entry>"
}