AI RESEARCH
CoDial: Interpretable Task-Oriented Dialogue Systems Through Dialogue Flow Alignment
arXiv CS.CL
•
ArXi:2506.02264v3 Announce Type: replace Building Task-Oriented Dialogue (TOD) systems that generalize across different tasks remains a challenging problem. Data-driven approaches often struggle to transfer effectively to unseen tasks. While recent schema-based TOD frameworks improve generalization by decoupling task logic from language understanding, their reliance on neural or generative models often obscures how task schemas influence behaviour and hence impair interpretability. In this work, we.