Papers › GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-Supervised...
GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-Supervised Learning and Explicit Policy Injection
Wanwei He, Yinpei Dai, Yinhe Zheng, Yuchuan Wu, Zheng Cao, Dermot Liu, Peng Jiang, Min Yang, Fei Huang, Luo Si, Jian Sun, Yongbin Li
Pre-trained models have proved to be powerful in enhancing task-oriented dialog systems. However, current pre-training methods mainly focus on enhancing dialog understanding and generation tasks while neglecting the exploitation of dialog policy. In this paper, we propose GALAXY, a novel pre-trained dialog model that explicitly learns dialog policy from limited labeled dialogs and large-scale unlabeled dialog corpora via semi-supervised learning. Specifically, we introduce a dialog act prediction task for policy optimization during pre-training and employ a consistency regularization term to refine the learned representation with the help of unlabeled dialogs. We also implement a gating mechanism to weigh suitable unlabeled dialog samples. Empirical results show that GALAXY substantially improves the performance of task-oriented dialog systems, and achieves new state-of-the-art results on benchmark datasets: In-Car, MultiWOZ2.0 and MultiWOZ2.1, improving their end-to-end combined scores by 2.5, 5.3 and 5.5 points, respectively. We also show that GALAXY has a stronger few-shot ability than existing models under various low-resource settings.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| End-To-End Dialogue Modelling | MULTIWOZ 2.0 | GALAXY | BLEU | 20.5 | #1 of 6 | Archive leaderboard | report |
| End-To-End Dialogue Modelling | MULTIWOZ 2.0 | GALAXY | MultiWOZ (Inform) | 94.4 | #1 of 6 | Archive leaderboard | report |
| End-To-End Dialogue Modelling | MULTIWOZ 2.0 | GALAXY | MultiWOZ (Success) | 85.3 | #1 of 6 | Archive leaderboard | report |
| End-To-End Dialogue Modelling | MULTIWOZ 2.1 | GALAXY | BLEU | 20.01 | #1 of 4 | Archive leaderboard | report |
| End-To-End Dialogue Modelling | MULTIWOZ 2.1 | GALAXY | MultiWOZ (Inform) | 95.30 | #1 of 4 | Archive leaderboard | report |
| End-To-End Dialogue Modelling | MULTIWOZ 2.1 | GALAXY | MultiWOZ (Success) | 86.20 | #1 of 4 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections