Kelvin Han

question generation (3) group relative policy optimisation (2) knowledge distillation (2) language model (2) reward model (2) reinforcement learning (2) question decomposition (1) natural language generation (1) question answering (1) multimodal learning (1) few-shot learning (1) synthetic data generation (1) distribution shift (1) knowledge graph (1) sub-question generation (1) question under discussion (1) few-shot prompting (1) policy optimization (1) domain generalization (1) large language model (1)