Yiran Liu

large language model (5) gender bia (2) causal inference (2) adversarial attack (2) social bias measurement (2) probe optimization (2) weakly supervised learning (1) self-attention mechanism (1) reinforcement learning (1) instruction tuning (1) model alignment (1) euclidean space (1) language model alignment (1) convolutional neural network (1) catastrophic forgetting (1) dual-space learning (1) video violence detection (1) preference alignment (1) euclidean geometry (1) hyperbolic representation (1)