We introduce SafeAligner, a novel method to enhance the security of large language models (LLMs) against jailbreak attacks. SafeAligner uses two specially trained models—the Sentinel Model for safety ...

Abstract: The task of table-to-text generation involves summarizing and creating natural language descriptions of tables. Previous approaches have used sequence-to-sequence generation methods, which ...

Abstract: Sample alignment is recognized as a vital component of vertical federated learning, which facilitates the integration of differential samples and high-quality model training. In this trend, ...