CoDial: Interpretable Task-Oriented Dialogue Systems Through Dialogue Flow Alignment
This work addresses the problem of interpretability and generalization in task-oriented dialogue systems for developers and users in high-stakes domains, though it is incremental by building on schema-based frameworks.
The paper tackles the challenge of building interpretable and generalizable task-oriented dialogue systems by introducing CoDial, a framework that converts task schemas into programmatic LLM guardrails, achieving state-of-the-art performance on the STAR dataset and competitive results on MultiWOZ while enabling iterative improvement through feedback.
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), which converts a TOD task schema, represented as a novel structured heterogeneous graph, to programmatic LLM guardrailing code, such as NVIDIA's Colang, enabling interpretable and efficient alignment of dialogue policies during inference. We introduce two paradigms, $\text{CoDial}_{\text{free}}$ and $\text{CoDial}_{\text{structured}}$ for generating LLM guardrails, and propose a feedback mechanism that integrates human feedback to iteratively improve the generated code. Empirically, CoDial achieves state-of-the-art (SOTA) performance on the widely used STAR dataset and is on par with SOTA on the MultiWOZ dataset, while also providing interpretability. We additionally demonstrate CoDial's iterative improvement via manual and LLM-aided feedback, making it a practical tool for expert-guided alignment of LLMs in high-stakes domains.