Saved in:
Bibliographic Details
Main Authors: Gatti, Andrea, Mascardi, Viviana, Ferrando, Angelo
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2411.14368
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910707421806592
author Gatti, Andrea
Mascardi, Viviana
Ferrando, Angelo
author_facet Gatti, Andrea
Mascardi, Viviana
Ferrando, Angelo
contents Chatbots have become integral to various application domains, including those with safety-critical considerations. As a result, there is a pressing need for methods that ensure chatbots consistently adhere to expected, safe behaviours. In this paper, we introduce RV4Chatbot, a Runtime Verification framework designed to monitor deviations in chatbot behaviour. We formalise expected behaviours as interaction protocols between the user and the chatbot. We present the RV4Chatbot design and describe two implementations that instantiate it: RV4Rasa, for monitoring chatbots created with the Rasa framework, and RV4Dialogflow, for monitoring Dialogflow chatbots. Additionally, we detail experiments conducted in a factory automation scenario using both RV4Rasa and RV4Dialogflow.
format Preprint
id arxiv_https___arxiv_org_abs_2411_14368
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle RV4Chatbot: Are Chatbots Allowed to Dream of Electric Sheep?
Gatti, Andrea
Mascardi, Viviana
Ferrando, Angelo
Artificial Intelligence
Human-Computer Interaction
Software Engineering
Chatbots have become integral to various application domains, including those with safety-critical considerations. As a result, there is a pressing need for methods that ensure chatbots consistently adhere to expected, safe behaviours. In this paper, we introduce RV4Chatbot, a Runtime Verification framework designed to monitor deviations in chatbot behaviour. We formalise expected behaviours as interaction protocols between the user and the chatbot. We present the RV4Chatbot design and describe two implementations that instantiate it: RV4Rasa, for monitoring chatbots created with the Rasa framework, and RV4Dialogflow, for monitoring Dialogflow chatbots. Additionally, we detail experiments conducted in a factory automation scenario using both RV4Rasa and RV4Dialogflow.
title RV4Chatbot: Are Chatbots Allowed to Dream of Electric Sheep?
topic Artificial Intelligence
Human-Computer Interaction
Software Engineering
url https://arxiv.org/abs/2411.14368