Lei Sha

large language model (7) text generation (4) unsupervised learning (3) dialogue system (3) adversarial attack (3) adversarial learning (3) llm safety (2) benchmark evaluation (2) safety training (2) jailbreak defense (2) pre-trained language model (2) representation learning (2) pretrained language model (2) dialog generation (2) model safety (2) knowledge graph (2) adversarial training (2) item recommendation (2) language model (2) conversational recommendation (2)