Yuxi Sun

large language model (3) contrastive learning (2) language model (2) social norm (2) valence prediction (2) ethical assessment (2) text summarization (1) knowledge graph (1) benchmark dataset (1) zero-shot learning (1) hallucination mitigation (1) steering vector (1) faithful explanation (1) character fidelity (1) social interaction (1) moral reasoning (1) text-to-table generation (1) role-playing large language model (1) interactive hallucination (1) stance transfer (1)