SemRoDe: Macro Adversarial Training to Learn Representations That are Robust to Word-Level Attacks

1 code implementation • 27 Mar 2024 • Brian Formento, Wenjie Feng, Chuan Sheng Foo, Luu Anh Tuan, See-Kiong Ng

Language models (LMs) are indispensable tools for natural language processing tasks, but their vulnerability to adversarial attacks remains a concern.

Word Embeddings