用可执行代码追踪对话状态，提升任务型对话准确性
PyTOD: Programmable Task-Oriented Dialogue with Execution Feedback
- 用生成代码替代规则约束，实现更灵活的状态追踪
- 在SGD基准上达到当前最优状态跟踪效果
- 适合需要高精度任务执行的对话系统研究者
可编程任务型对话（TOD）代理使语言模型能够遵循结构化对话策略，但其效果依赖于准确的状态追踪。我们提出PyTOD，该代理通过生成可执行代码来追踪对话状态，并利用策略与执行反馈实现高效错误修正。为此，PyTOD采用一种简单的约束解码方法，使用语言模型而非语法规则来遵循API模式。这使得其在具有挑战性的SGD基准上取得了最先进的状态追踪性能。实验表明，随着对话进行，PyTOD在准确性和用户目标估计鲁棒性方面均优于强基线模型，证明了执行感知状态追踪的有效性。
原文摘要 · Abstract (English)
Programmable task-oriented dialogue (TOD) agents enable language models to follow structured dialogue policies, but their effectiveness hinges on accurate state tracking. We present PyTOD, an agent that generates executable code to track dialogue state and uses policy and execution feedback for efficient error correction. To this end, PyTOD employs a simple constrained decoding approach, using a language model instead of grammar rules to follow API schemata. This leads to state-of-the-art state tracking performance on the challenging SGD benchmark. Our experiments show that PyTOD surpasses strong baselines in both accuracy and robust user goal estimation as the dialogue progresses, demonstrating the effectiveness of execution-aware state tracking.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。