Ding, Y., Niu, J., & Yi, P. (2025). MBTSAD: Mitigating Backdoors in Language Models Based on Token Splitting and Attention Distillation.
Chicago-Zitierstil (17. Ausg.)Ding, Yidong, Jiafei Niu, und Ping Yi. MBTSAD: Mitigating Backdoors in Language Models Based on Token Splitting and Attention Distillation. 2025.
MLA-Zitierstil (9. Ausg.)Ding, Yidong, et al. MBTSAD: Mitigating Backdoors in Language Models Based on Token Splitting and Attention Distillation. 2025.
Achtung: Diese Zitate sind unter Umständen nicht zu 100% korrekt.