← NSFGrants
HomeNsf Awards

CAREER: A Safety-Aware Learning Framework for Identifying and Mitigating Risks in Human-LL — NSF Award to University of California

Large language models are increasingly used in healthcare applications such as virtual assistants and decision support tools, offering new opportunities to improve access to care and patient outcomes. However, these systems can introduce new kinds of risks that arise not from the model alone, but from how people intera

Award titleCAREER: A Safety-Aware Learning Framework for Identifying and Mitigating Risks in Human-LL
Award ID2541748
AwardeeUniversity of California-Santa Cruz
CitySANTA CRUZ
StateCA
Amount obligated$349,875
Principal investigatorChenguang Wang
ProgramInfo Integration & Informatics
Start date10/01/2026
AbstractLarge language models are increasingly used in healthcare applications such as virtual assistants and decision support tools, offering new opportunities to improve access to care and patient outcomes. However, these systems can introduce new kinds of risks that arise not from the model alone, but from how people interact with it. For example, patients may rely too heavily on automated advice, receive responses shaped by harmful preconceptions or be unintentionally influenced toward unsafe decisi
SourceNSF Awards

🔍 Search all NSF awards →