ZHANG, X.; ZHENG, B.; HU, J.; LI, C.; BAI, X. From Toxic to Trustworthy: Using Self-Distillation and Semi-supervised Methods to Refine Neural Networks. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 38, n. 15, p. 16873-16880, 2024. DOI: 10.1609/aaai.v38i15.29629. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/29629. Acesso em: 16 jul. 2024.