WANG, Bo; LI, Junzhuo; CHEN, Hong; CHU, Yuanlin; FAN, Yuxuan; HU, Xuming. Deconstructing Pre-training: Knowledge Attribution Analysis in MoE and Dense Models. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 39, p. 33359–33367, 2026. DOI: 10.1609/aaai.v40i39.40622. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/40622. Acesso em: 16 may. 2026.