Data Science Professor Receives NSF Grant to Explore How Generative AI Can Generate K-12 Test Questions

Societal understanding of how artificial intelligence will transform education in the years ahead remains in its early stages, but a newly funded project from researchers at the University of Virginia may shed light on one key area: Can generative AI tools be used to develop high-quality test items for K-12 schools?

The School of Data Science is pleased to announce that the National Science Foundation has awarded a grant to a team of researchers, led by Sheng Li, a Quantitative Foundation Associate Professor of Data Science, to examine the feasibility of using generative AI to create questions for K-12 standardized testing, language testing, and other assessment needs. 

Li, as principal investigator, will work with two doctoral students at the School of Data Science — Dongliang Guo and Daiqing Qi — as well as pscychometricians from educational testing companies. 

The yearlong grant totaling $50,000 was awarded through the NSF’s I-Corps program, which was launched in 2011 as a way to allow research teams to quickly determine the market potential of their innovations through the customer discovery process. A goal is to provide scientists and scholars the opportunity to enhance the societal impact of their NSF-funded research endeavors.

Developing high-quality test items has long been a laborious, time-consuming, and expensive process.  Li and his team hope that their automatic item generation and evaluation system could be used by a variety of stakeholders — including K-12 testing companies, language testing agencies, and online education platforms — to reduce these burdens while still producing test questions that align with required specifications and ensure fairness.

The team will also collaborate with UVA’s Licensing & Ventures Group on patent applications.