JIN, Haotian; LI, Yang; FAN, Haihui; SHEN, Lin; LI, Xiangfang; LI, Bo. Uncovering and Aligning Anomalous Attention Heads to Defend Against NLP Backdoor Attacks. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 44, p. 37472–37480, 2026. DOI: 10.1609/aaai.v40i44.41080. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/41080. Acesso em: 25 may. 2026.