國立高雄大學圖資館 |

登入

回首頁

Towards Practice-Integrated Human-AI Systems for Developing High-Quality Educational Assessments /

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Towards Practice-Integrated Human-AI Systems for Developing High-Quality Educational Assessments /Yuan Charles Cui.
作者:	Cui, Yuan Charles,
面頁冊數:	1 electronic resource (160 pages)
附註:	Source: Dissertations Abstracts International, Volume: 87-06, Section: A.
附註:	Advisors: Kay, Matthew Committee members: O'Rourke, Eleanor; Horn, Michael; Yang, Fumeng.
Contained By:	Dissertations Abstracts International87-06A.
標題:	Computer science.
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=32284541
ISBN:	9798265482525

Towards Practice-Integrated Human-AI Systems for Developing High-Quality Educational Assessments /
Cui, Yuan Charles,

Towards Practice-Integrated Human-AI Systems for Developing High-Quality Educational Assessments /Yuan Charles Cui. - 1 electronic resource (160 pages)

Source: Dissertations Abstracts International, Volume: 87-06, Section: A.

Assessments are foundational to education, shaping how teachers teach, how students learn, and how accountability is maintained across the educational ecosystem. Yet, creating high‐quality assessments remains one of the most time‐consuming aspects of teaching. Educators, especially those in under‐resourced schools, often lack the time, training, and support to design effective assessments that are aligned with curricula and diverse student needs. While recent advances in large language models (LLMs) show the potential to reduce this burden, they also raise concerns about quality and teacher trust. In specific domains such as data visualization education, researchers and educators face similar challenges: existing assessments for measuring visualization literacy (the ability to read and interpret visualizations) are lengthy, rigid, and difficult to scale or adapt. Across both general and visualization‐specific contexts, improving efficiency, maintaining quality, and building trust in assessment development and delivery requires systems that lower technical barriers, promote content reuse and adaptation, and integrate meaningfully into educators' existing workflows. This dissertation addresses these challenges through three complementary projects that develop adaptive, scalable, practice-integrated solutions for assessment development. The first project introduces A‐VLAT and A‐CALVI, computerized adaptive tests for visualization literacy that maintain precision and reliability while halving test length. The second project presents the VILA pipeline that leverages LLMs to generate visualization literacy questions at scale, combining automated generation with expert‐driven evaluation to ensure quality and validity. The third project extends these ideas to general K-12 education, where we codesigned a web-based system, Ripplet, that supports multilevel reusable interactions with LLMs for creating, editing, and adapting assessments. Together, these projects contribute to the development of assessment systems that improve efficiency, scalability, and quality.

English

ISBN: 9798265482525Subjects--Topical Terms:

199325
Computer science.
Subjects--Index Terms:

AI for education

Towards Practice-Integrated Human-AI Systems for Developing High-Quality Educational Assessments /
LDR:03700nmm a22004693i 4500 001 693780
005 20260511063023.5
006 m o d
007 cr|nu||||||||
008 260819s2025 miu||||||m |||||||eng d
020 $a 9798265482525
035 $a (MiAaPQD)AAI32284541
035 $a AAI32284541
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Cui, Yuan Charles, $e author. $3 1010456
245 1 0 $a Towards Practice-Integrated Human-AI Systems for Developing High-Quality Educational Assessments / $c Yuan Charles Cui.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2025
300 $a 1 electronic resource (160 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 87-06, Section: A.
500 $a Advisors: Kay, Matthew Committee members: O'Rourke, Eleanor; Horn, Michael; Yang, Fumeng.
502 $b Ph.D. $c Northwestern University $d 2025.
520 $a Assessments are foundational to education, shaping how teachers teach, how students learn, and how accountability is maintained across the educational ecosystem. Yet, creating high‐quality assessments remains one of the most time‐consuming aspects of teaching. Educators, especially those in under‐resourced schools, often lack the time, training, and support to design effective assessments that are aligned with curricula and diverse student needs. While recent advances in large language models (LLMs) show the potential to reduce this burden, they also raise concerns about quality and teacher trust. In specific domains such as data visualization education, researchers and educators face similar challenges: existing assessments for measuring visualization literacy (the ability to read and interpret visualizations) are lengthy, rigid, and difficult to scale or adapt. Across both general and visualization‐specific contexts, improving efficiency, maintaining quality, and building trust in assessment development and delivery requires systems that lower technical barriers, promote content reuse and adaptation, and integrate meaningfully into educators' existing workflows. This dissertation addresses these challenges through three complementary projects that develop adaptive, scalable, practice-integrated solutions for assessment development. The first project introduces A‐VLAT and A‐CALVI, computerized adaptive tests for visualization literacy that maintain precision and reliability while halving test length. The second project presents the VILA pipeline that leverages LLMs to generate visualization literacy questions at scale, combining automated generation with expert‐driven evaluation to ensure quality and validity. The third project extends these ideas to general K-12 education, where we codesigned a web-based system, Ripplet, that supports multilevel reusable interactions with LLMs for creating, editing, and adapting assessments. Together, these projects contribute to the development of assessment systems that improve efficiency, scalability, and quality.
546 $a English
590 $a School code: 0163
650 4 $a Computer science. $3 199325
650 4 $a Education. $3 177995
650 4 $a Educational technology. $3 222132
650 4 $a Educational evaluation. $3 180577
653 $a AI for education
653 $a Data visualization
653 $a Educational assessment
653 $a Human-AI collaboration
653 $a Human-AI interaction
653 $a Large language models
690 $a 0984
690 $a 0800
690 $a 0515
690 $a 0443
690 $a 0710
710 2 $a Northwestern University. $b Computer Science. $3 660391
720 1 $a Kay, Matthew $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 87-06A.
790 $a 0163
791 $a Ph.D.
792 $a 2025
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=32284541