Jin, H., Li, Y., Fan, H., Shen, L., Li, X., & Li, B. (2026). Uncovering and Aligning Anomalous Attention Heads to Defend Against NLP Backdoor Attacks. Proceedings of the AAAI Conference on Artificial Intelligence, 40(44), 37472–37480. https://doi.org/10.1609/aaai.v40i44.41080