Think Again! The Effect of Test-Time Compute on Preferences, Opinions, and Beliefs of Large Language Models
Paper • 2505.19621 • Published • 4
George Kour
gkour
·
AI & ML interests
George Kour's research focuses on enhancing the safety, reliability, and ethical use of artificial intelligence, particularly in natural language processing and machine learning, by identifying vulnerabilities in large language models, developing innovative data augmentation methods, and establishing robust evaluation metrics to mitigate risks associated with AI outputs.
Recent Activity
published a dataset about 13 hours ago
gkour/israeli_law updated a dataset about 13 hours ago
gkour/israeli_law updated a dataset 6 months ago
gkour/israeli_lawOrganizations
