Valentina Pyatkin

Reinforcement Learning (1)

large language model (6) semantic analysis (5) natural language understanding (4) reward model (3) language model (2) value alignment (2) commonsense reasoning (2) fine-grained classification (2) language model alignment (2) semantic role labeling (2) few-shot learning (2) reinforcement learning from human feedback (2) reinforcement learning (2) text classification (2) question answering (2) natural language processing (2) zero-shot learning (2) text generation (2) semantic parsing (2) text representation (2)