@inproceedings{wen-etal-2025-guideline,
    title = "Guideline Compliance in Task-Oriented Dialogue: The Chained Prior Approach",
    author = "Wen, Xiangyu  and
      Zhong, Jianyuan  and
      Xu, Zhijian  and
      Xu, Qiang",
    editor = "Chiruzzo, Luis  and
      Ritter, Alan  and
      Wang, Lu",
    booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/Ingest-2025-COMPUTEL/2025.findings-naacl.377/",
    pages = "6750--6776",
    ISBN = "979-8-89176-195-7",
    abstract = "Task-oriented dialogue (TOD) systems are widely used across various domains, including customer service, appointment scheduling, and technical support. In real-world scenarios, such systems must adhere to given operational guidelines. However, existing solutions based on large language models often cannot achieve strict guideline compliance, even when fine-tuned with domain knowledge. To address this issue, we introduce a novel TOD system named GuidedTOD, which explicitly considers domain-specific guidelines by integrating a policy module. This module employs a Markov Chain, termed Chained Prior, to efficiently encode and dynamically update guideline knowledge. During inference, the Chained Prior re-ranks outputs from the domain-expert language model using beam search, ensuring guideline adherence. Experimental results show that GuidedTOD significantly improves guideline compliance, achieving approximately 20{\%} better action prediction accuracy than state-of-the-art solutions. Code is available here: https://github.com/cure-lab/GuidedTOD."
}