← NSFGrants
HomeNsf Awards

Nonparametric causal factor models for reliable generative AI — NSF Award to University of Chicago (IL, $200,000)

Modern artificial intelligence systems produce striking images, text, and other creative outputs, but it is often unclear what these systems have actually learned internally. This makes it difficult to ensure that these models are reliable, safe, and trustworthy when deployed in the real world. Although these models ca

Award titleNonparametric causal factor models for reliable generative AI
Award ID2610618
AwardeeUniversity of Chicago
CityCHICAGO
StateIL
Amount obligated$200,000
Principal investigatorNikhyl Aragam
ProgramSTATISTICS
Start date06/01/2026
AbstractModern artificial intelligence systems produce striking images, text, and other creative outputs, but it is often unclear what these systems have actually learned internally. This makes it difficult to ensure that these models are reliable, safe, and trustworthy when deployed in the real world. Although these models can imitate patterns in data, the process through which they do so does not necessarily correspond to meaningful causes, stable mechanisms, or interpretable concepts that stakeholder
SourceNSF Awards

🔍 Search all NSF awards →