Qianyu Wang

large language model (2) transfer learning (1) self-supervised learning (1) question answering (1) instruction following (1) knowledge graph (1) reward hacking (1) language model (1) multi-hop question answering (1) multi-hop reasoning (1) semantic reasoning (1) entity alignment (1) semantic understanding (1) iterative reasoning (1) reasoning trajectory (1) knowledge graph integration (1) curriculum reinforcement learning (1) zero-shot learning (1) reinforcement learning from verifiable reward (1)