Hannah Rose Kirk

large language model (3) human feedback (2) domain adaptation (1) text classification (1) preference learning (1) in-context learning (1) model evaluation (1) cross-domain learning (1) responsible ai (1) reinforcement learning from human feedback (1) model alignment (1) abuse detection (1) preference modeling (1) low-resource language (1) language model (1) value alignment (1) data quality (1) feedback learning (1) dataset benchmark (1) data-centric ai (1)