Changyue Wang

large language model (3) hallucination detection (2) knowledge editing (2) in-context editing (2) multi-hop reasoning (1) chain of thought (1) knowledge injection (1) knowledge updating (1) knowledge update (1) internal state (1) large reasoning model (1) real-time detection (1) reasoning consistency (1) reasoning integrity (1) unsupervised learning (1) entropy-based uncertainty (1) in-context learning (1) prompt engineering (1) semantic alignment (1)