Dialog Flow Induction for Constrainable LLM-Based Chatbots
This addresses the issue of inaccurate and irrelevant responses in domain-specific applications like healthcare and customer service, though it appears incremental as it builds on existing dialog flow methods.
The paper tackles the problem of ensuring LLM-based chatbots stay within specialized domain boundaries by introducing an unsupervised approach for automatically inducing domain-specific dialog flows, demonstrating through evaluations that their data-guided dialog flows achieve better domain coverage than manual crafting.
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.