He W, Dai Y, Zheng Y, Wu Y, Cao Z, Liu D, et al. GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-supervised Learning and Explicit Policy Injection. AAAI [Internet]. 2022 Jun. 28 [cited 2026 May 27];36(10):10749-57. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/21320