Eric Mitchell

large language model (5) language model (4) reinforcement learning from human feedback (3) direct preference optimization (2) offline reinforcement learning (2) online adaptation (2) imitation learning (1) online learning (1) reinforcement learning (1) model calibration (1) model editing (1) knowledge editing (1) natural language inference (1) question answering (1) uncertainty quantification (1) language model alignment (1) instruction following (1) text classification (1) confidence calibration (1) preference optimization (1)