RV4Chatbot: Are Chatbots Allowed to Dream of Electric Sheep?

Andrea Gatti, Viviana Mascardi, Angelo Ferrando
11/21/2024
cs.AIcs.HCcs.SE

No confident code implementation found for this paper.

Abstract

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Cite this paper

@article{gatti2024rvchatbot,
  title  = {RV4Chatbot: Are Chatbots Allowed to Dream of Electric Sheep?},
  author = {Andrea Gatti and Viviana Mascardi and Angelo Ferrando},
  year   = {2024},
  eprint = {2411.14368},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2411.14368v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2411.14368.svg)](https://codeofpaper.com/paper/2411.14368)

Discussion