ConEX: A Context-Aware Framework for Enhancing Explanation Systems

Yasmeen Khaled, Nourhan Ehab

2024

Abstract

Recent advances in Artificial Intelligence (AI) have led to the widespread adoption of intricate AI models, raising concerns about their opaque decision-making. Explainable AI (XAI) is crucial for improving transparency and trust. However, current XAI approaches often prioritize AI experts, neglecting broader stakeholder requirements. This paper introduces a comprehensive context taxonomy and ConEX, an adaptable framework for context-sensitive explanations. ConEX includes explicit problem-solving knowledge and contextual insights, allowing tailored explanations for specific contexts. We apply the framework to personalize movie recommendations by aligning explanations with user profiles. Additionally, we present an empirical user study highlighting diverse preferences for contextualization depth in explanations, highlighting the importance of catering to these preferences to foster trust and satisfaction in AI systems.

Paper Citation

in Harvard Style

Khaled Y. and Ehab N. (2024). ConEX: A Context-Aware Framework for Enhancing Explanation Systems. In Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART; ISBN 978-989-758-680-4, SciTePress, pages 699-706. DOI: 10.5220/0012385300003636

in Bibtex Style

@conference{icaart24,
author={Yasmeen Khaled and Nourhan Ehab},
title={ConEX: A Context-Aware Framework for Enhancing Explanation Systems},
booktitle={Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART},
year={2024},
pages={699-706},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012385300003636},
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 - ConEX: A Context-Aware Framework for Enhancing Explanation Systems
SN - 978-989-758-680-4
AU - Khaled Y.
AU - Ehab N.
PY - 2024
SP - 699
EP - 706
DO - 10.5220/0012385300003636
PB - SciTePress