Jin H, Li Y, Fan H, Shen L, Li X, Li B. Uncovering and Aligning Anomalous Attention Heads to Defend Against NLP Backdoor Attacks. AAAI [Internet]. 2026 Mar. 14 [cited 2026 May 25];40(44):37472-80. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/41080