@inproceedings{shayanfar-etal-2026-codial,
    title = "{C}o{D}ial: Interpretable Task-Oriented Dialogue Systems Through Dialogue Flow Alignment",
    author = "Shayanfar, Radin  and
      Luo, Chu Fei  and
      Bhambhoria, Rohan V  and
      Dahan, Samuel  and
      Zhu, Xiaodan",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.1980/",
    pages = "42741--42763",
    ISBN = "979-8-89176-390-6",
    abstract = "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 introduce a novel framework, CoDial (Code for Dialogue), at the core of which is converting a predefined task schema to a structured heterogeneous graph and then to popular programmatic LLM guardrailing code, such as NVIDIA{'}s Colang. The pipeline enables efficient and interpretable alignment of dialogue policies during inference. We introduce two paradigms for LLM guardrailing code generation, CoDial-free and CoDial-structured, and propose a mechanism that integrates human feedback to iteratively improve the generated code. Empirically, CoDial achieves state-of-the-art (SOTA) performance on the widely used benchmark datasets, while providing inherent interpretability in the design. We additionally demonstrate CoDial{'}s iterative improvement via manual and LLM-aided feedback, making it a practical tool for human-guided alignment of LLMs in unseen domains."
}