通过对话流程对齐构建可解释的任务导向对话系统：CoDial
CoDial: Interpretable Task-Oriented Dialogue Systems Through Dialogue Flow Alignment
AI总结：
CoDial通过将预定义任务 schema 转换为结构化异构图并生成程序化 LLM 防御代码，实现对话策略的高效可解释对齐，提升任务导向对话系统的泛化能力与可解释性。
摘要：
构建能够跨不同任务泛化任务导向对话（TOD）系统仍是一个具有挑战性的问题。数据驱动方法往往难以有效迁移至未见过的任务。虽然最近基于模式的TOD框架通过将任务逻辑与语言理解解耦来提高泛化能力，但其对神经或生成模型的依赖常常掩盖了任务模式如何影响行为，从而影响可解释性。在本工作中，我们引入了一个新的框架CoDial（对话代码），其核心是将预定义的任务模式转换为结构化的异构图，然后转换为程序化的LLM防御代码，如NVIDIA的Colang。该流程在推理过程中实现了对话策略的高效且可解释的对齐。我们引入了两种LLM防御代码生成范式，CoDial_free和CoDial_structured，并提出了一种机制，通过整合人类反馈来迭代改进生成的代码。经验上，CoDial在广泛使用的基准数据集上实现了最先进的性能，同时在设计中提供内在的可解释性。我们还通过手动和LLM辅助反馈展示了CoDial的迭代改进，使其成为在未见过的领域中人类引导LLM对齐的实用工具。
英文摘要：
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 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, $\text{CoDial}_{\text{free}}$ and $\text{CoDial}_{\text{structured}}$, 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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
