Models with Verbally Enunciated Explanations: Towards Safe, Accountable, and Trustworthy Artificial Intelligence

Mattias Wahde

2024

Abstract

In this position paper, we propose a new approach to artificial intelligence (AI), involving systems, abbreviated MOVEEs, that are capable of generating a verbally enunciated explanation of their actions, such that the explanation is also correct by construction. The possibility of obtaining a human-understandable, verbal explanation of any action or decision taken by an AI system is highly desirable, and is becoming increasingly important at this time when many AI systems operate as inscrutable black boxes. We describe the desirable properties of the proposed systems, contrasting them with existing AI approaches. We also discuss limitations and possible applications. While the discussion is mostly held in general terms, we also provide a specific example of a completed system, as well as a few examples of ongoing and future work.

Paper Citation

in Harvard Style

Wahde M. (2024). Models with Verbally Enunciated Explanations: Towards Safe, Accountable, and Trustworthy Artificial Intelligence. In Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART; ISBN 978-989-758-680-4, SciTePress, pages 101-108. DOI: 10.5220/0012307100003636

in Bibtex Style

@conference{icaart24,
author={Mattias Wahde},
title={Models with Verbally Enunciated Explanations: Towards Safe, Accountable, and Trustworthy Artificial Intelligence},
booktitle={Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART},
year={2024},
pages={101-108},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012307100003636},
isbn={978-989-758-680-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART
TI - Models with Verbally Enunciated Explanations: Towards Safe, Accountable, and Trustworthy Artificial Intelligence
SN - 978-989-758-680-4
AU - Wahde M.
PY - 2024
SP - 101
EP - 108
DO - 10.5220/0012307100003636
PB - SciTePress