Dialog Flow Induction for Constrainable LLM-Based Chatbots

Autor:	Agrawal, Stuti, Uppuluri, Nishi, Pillai, Pranav, Reddy, Revanth Gangi, Li, Zoey, Tur, Gokhan, Hakkani-Tur, Dilek, Ji, Heng
Rok vydání:	2024
Předmět:	Computer Science - Computation and Language
Druh dokumentu:	Working Paper
Popis:	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 various 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. Comment: Accepted at SIGDIAL 2024
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2408.01623 Zobrazit plný text záznamu View this record from Arxiv