Lian Lian

large language model (3) instruction tuning (2) curriculum learning (1) machine translation (1) preference optimization (1) instruction following (1) model alignment (1) data sampling (1) consistency learning (1) knowledge retention (1) domain-specific fine-tuning (1) preference training (1) data partitioning (1) error amplification (1) curriculum consistency learning (1) reinforcement learning (1) conditional sentence generation (1) continual learning (1)