Tag
This paper proposes MLJailDe, a multilingual jailbreak detection framework that uses back-translation data augmentation and relative-distance constraints to improve cross-lingual generalization and robustness, achieving 98.5% F1 score across 11 languages.
This paper introduces a direct sign-to-sign translation model that bypasses intermediate text by using back-translation to create synthetic parallel sign language data, achieving significant improvements in speed and accuracy over cascade methods for ASL, CSL, and DGS.