Jiang P, Lyu X, Li Y, Ma J. Backdoor Token Unlearning: Exposing and Defending Backdoors in Pretrained Language Models. AAAI [Internet]. 2025 Apr. 11 [cited 2026 May 27];39(23):24285-93. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/34605