Pareto stationary solution that is not improvable for all objectives without sacrificing some objectives.

To tackle the limitations, we introduce SpokenWOZ, a large-scale speech-text dataset for spoken TOD, containing 8 domains, 203k turns, 5.7k dialogues and 249 hours of audios from human-to-human spoken

We show how to "compile" human-readable programs into standard decoder-only transformer models.

General decision intelligence needs to solve tasks in many distinct domains.

CaST, which consistently outperforms existing methods with good interpretability.