Dialog Flow Induction for Constrainable LLM-Based Chatbots
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913457685659648 |
|---|---|
| author | Agrawal, Stuti Uppuluri, Nishi Pillai, Pranav Reddy, Revanth Gangi Li, Zoey Tur, Gokhan Hakkani-Tur, Dilek Ji, Heng |
| author_facet | Agrawal, Stuti Uppuluri, Nishi Pillai, Pranav Reddy, Revanth Gangi Li, Zoey Tur, Gokhan Hakkani-Tur, Dilek Ji, Heng |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_01623 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Dialog Flow Induction for Constrainable LLM-Based Chatbots Agrawal, Stuti Uppuluri, Nishi Pillai, Pranav Reddy, Revanth Gangi Li, Zoey Tur, Gokhan Hakkani-Tur, Dilek Ji, Heng Computation and Language 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. |
| title | Dialog Flow Induction for Constrainable LLM-Based Chatbots |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2408.01623 |