← NSFGrants
HomeNsf Awards

CAREER: OPENALIGN: Towards Open-World Preference Alignment for Large Language Models — NSF Award to Northwestern University at Chi

As artificial intelligence (AI) systems are increasingly deployed in critical domains such as healthcare, scientific discovery, and autonomous decision-making, ensuring that foundation AI models such as large language models (LLMs) align with human values and preferences has become essential for their safe and benefici

Award titleCAREER: OPENALIGN: Towards Open-World Preference Alignment for Large Language Models
Award ID2544599
AwardeeNorthwestern University at Chicago
CityEVANSTON
StateIL
Amount obligated$419,999
Principal investigatorKaize Ding
ProgramInfo Integration & Informatics
Start date10/01/2026
AbstractAs artificial intelligence (AI) systems are increasingly deployed in critical domains such as healthcare, scientific discovery, and autonomous decision-making, ensuring that foundation AI models such as large language models (LLMs) align with human values and preferences has become essential for their safe and beneficial deployment. However, most existing approaches rely on large amounts of high-quality labeled preference data and assume clean, stable, well-controlled environments. These assumpt
SourceNSF Awards

🔍 Search all NSF awards →