HE, Wanwei et al. GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-supervised Learning and Explicit Policy Injection. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 36, n. 10, p. 10749–10757, 2022. DOI: 10.1609/aaai.v36i10.21320. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/21320. Acesso em: 27 may. 2026.