Federal Project Grant Award Summary

Florida State University received a $301,560 Project Grant from the National Science Foundation (NSF) Division of Computing and Communication Foundations under the Computer and Information Science and Engineering program (CFDA 47.070), effective October 1, 2026 through September 30, 2031. The award supports development of the Large Number Model (LNM), a hybrid neural-symbolic artificial intelligence system designed to accurately comprehend and reason over complex numerical and structured data, including units, formulas, metadata, and tabular information. The project addresses critical gaps in current AI models' ability to handle quantitative reasoning in high-stakes domains such as medicine, finance, defense, and space exploration.

The research deliverables encompass three primary components: scalable methods for extracting numerical and structured information from documents; model architectures that effectively represent quantities and two-dimensional tabular data; and symbolic validation mechanisms to ensure algebraic, dimensional, and semantic consistency. Additionally, the project will generate educational outcomes including new teaching materials, student research opportunities, and outreach activities focused on data reasoning. The work will advance trustworthy data-driven discovery and decision-making through controlled experiments, robustness testing, and evaluation against benchmark datasets drawn from scientific applications.