We present a set of capabilities allowing an agent planning with moral and social norms represented in temporal logic to respond to queries about its norms and behaviors in natural language, and for the human user to add and remove norms directly in natural language. The user may also pose hypothetical modifications to the agent's norms and inquire about their effects.
@article{arxiv.1911.00229,
title = {Engaging in Dialogue about an Agent's Norms and Behaviors},
author = {Daniel Kasenberg and Antonio Roque and Ravenna Thielstrom and Matthias Scheutz},
journal= {arXiv preprint arXiv:1911.00229},
year = {2019}
}
Comments
Accepted to the 1st Workshop on Interactive Natural Language Technology for Explainable Artificial Intelligence (NL4XAI)