Cristina Gârbacea

natural language generation (5) evaluation metrics (4) human evaluation (3) text simplification (2) ensemble learning (2) text complexity (2) explainable prediction (2) propaganda detection (2) reward function (1) reinforcement learning from human feedback (1) knowledge distillation (1) model alignment (1) policy optimization (1) neural network model (1) language model alignment (1) text classification (1) automated evaluation (1) best-of-n sampling (1) language model fine-tuning (1) data imbalance (1)