@inproceedings{agrawal-etal-2024-dialog,
    title = "Dialog Flow Induction for Constrainable {LLM}-Based Chatbots",
    author = "Agrawal, Stuti  and
      Pillai, Pranav  and
      Uppuluri, Nishi  and
      Gangi Reddy, Revanth  and
      Li, Sha  and
      Tur, Gokhan  and
      Hakkani-Tur, Dilek  and
      Ji, Heng",
    editor = "Kawahara, Tatsuya  and
      Demberg, Vera  and
      Ultes, Stefan  and
      Inoue, Koji  and
      Mehri, Shikib  and
      Howcroft, David  and
      Komatani, Kazunori",
    booktitle = "Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue",
    month = sep,
    year = "2024",
    address = "Kyoto, Japan",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.sigdial-1.6/",
    doi = "10.18653/v1/2024.sigdial-1.6",
    pages = "66--77",
    abstract = "LLM-driven dialog systems are used in a diverse set of applications, ranging from healthcare to customer service. However, given their generalization capability, it is difficult to ensure that these chatbots stay within the boundaries of the specialized domains, potentially resulting in inaccurate information and irrelevant responses. This paper introduces an unsupervised approach for automatically inducing domain-specific dialog flows that can be used to constrain LLM-based chatbots. We introduce two variants of dialog flow based on the availability of in-domain conversation instances. Through human and automatic evaluation over 24 dialog domains, we demonstrate that our high-quality data-guided dialog flows achieve better domain coverage, thereby overcoming the need for extensive manual crafting of such flows."
}