Federal Project Grant Award Summary

The University of Virginia received a $538,798 Project Grant from the National Science Foundation's Division of Computing and Communication Foundations (CFDA 47.070: Computer and Information Science and Engineering) awarded October 1, 2026, with completion targeted for September 30, 2031. This CAREER award funds research into structure-aware learning from weak supervision for knowledge acquisition—a paradigm enabling artificial intelligence (AI) systems to extract actionable insights from unstructured text without requiring massive, perfectly curated labeled datasets. The research develops novel methodologies, including a Spherical Hierarchical Expectation-Maximization algorithm and denoising retrieval-augmented approaches, to allow AI systems to learn autonomously from incomplete, noisy, and ambiguous data by discovering underlying semantic structures such as concept hierarchies and retrieval pathways.

The project delivers both research outputs and educational products. Primary deliverables include a unified framework bridging unstructured language data with structured knowledge representations, scalable information extraction and classification tools operable without predefined schemas, and domain-specific AI tools designed for resource-constrained environments serving public health agencies and community organizations. Additionally, the award integrates research outcomes into new undergraduate and graduate curricula, open-source educational toolkits, and K-12 outreach programs intended to broaden participation in computing and advance workforce development in reliable, human-centered AI systems development. Research is conducted in Charlottesville, Virginia.