Zhijie Tan

reinforcement learning (1) direct preference optimization (1) in-context learning (1) question answering (1) chain-of-thought reasoning (1) tree search (1) vision-language model (1) retrieval-augmented generation (1) graph reasoning (1) explainable artificial intelligence (1) subgraph sampling (1) group relative policy optimization (1) logical fallacy detection (1) domain-specific reasoning (1) multi-stage reasoning (1) large language model (1) order bia (1) reasoning audit-driven optimization (1) order fairness (1) dual group advantage optimization (1)