JIANG, Peihai; LYU, Xixiang; LI, Yige; MA, Jing. Backdoor Token Unlearning: Exposing and Defending Backdoors in Pretrained Language Models. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 39, n. 23, p. 24285–24293, 2025. DOI: 10.1609/aaai.v39i23.34605. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/34605. Acesso em: 27 may. 2026.