Dong Jin

large language model (3) table question answering (2) table pruning (2) preference optimization (1) sql generation (1) model alignment (1) model fine-tuning (1) data synthesis (1) database query (1) reinforcement learning (1) open-source model (1) tabular reasoning (1) domain-specific fine-tuning (1) parallel search (1) preference training (1) error amplification (1) sql reasoning (1) knowledge retention (1) continual learning (1) question decomposition (1)