Xi Cao

adversarial text generation (2) low-resource language (2) textual adversarial attack (2) model robustness (2) human-in-the-loop learning (1) safety alignment (1) black-box attack (1) pre-trained language model (1) chinese minority language (1) tibetan script (1) minority language (1) cross-lingual evaluation (1) dialect adaptation (1) lower-resource language (1) large language model (1) multitask benchmark (1) syllable-level attack (1) adversarial learning (1) object relational mapping (1) adversarial robustness (1)