Wang, Bo, Junzhuo Li, Hong Chen, Yuanlin Chu, Yuxuan Fan, and Xuming Hu. “Deconstructing Pre-Training: Knowledge Attribution Analysis in MoE and Dense Models”. Proceedings of the AAAI Conference on Artificial Intelligence 40, no. 39 (March 14, 2026): 33359–33367. Accessed May 16, 2026. https://ojs.aaai.org/index.php/AAAI/article/view/40622.