Demystifying XAI : Requirements for Understandable XAI Explanations
- This paper establishes requirements for assessing the usability of Explainable Artificial Intelligence (XAI) methods, focusing on non-AI experts like healthcare professionals. Through a synthesis of literature and empirical findings, it emphasizes achieving optimal cognitive load, task performance, and task time in XAI explanations. Key components include tailoring explanations to user expertise, integrating domain knowledge, and using non-propositional representations for comprehension. The paper highlights the critical role of relevance, accuracy, and truthfulness in fostering user trust. Practical guidelines are provided for designing transparent and user-friendly XAI explanations, especially in high-stakes contexts like healthcare. Overall, the paper's primary contribution lies in delineating clear requirements for effective XAI explanations, facilitating human-AI collaboration across diverse domains.
Download full text files
Additional Services
Statistics
| Author: | Jan StodtORCiDGND, Christoph ReichORCiDGND, Martin KnahlGND |
|---|---|
| URN: | https://urn:nbn:de:bsz:fn1-opus4-108055 |
| DOI: | https://doi.org/10.3233/SHTI240477 |
| ISBN: | 978-1-64368-533-5 |
| Parent Title (English): | Digital Health and Informatics : Innovations for Sustainable Health Care Systems; Proceedings of MIE 2024, 25–29 August 2024, Athens, Greece |
| Publisher: | IOS Press |
| Document Type: | Conference Proceeding |
| Language: | English |
| Year of Completion: | 2024 |
| Release Date: | 2024/09/12 |
| Tag: | Peer-reviewed conference |
| First Page: | 565 |
| Last Page: | 569 |
| Open-Access-Status: | Open Access |
| Gold | |
| Licence (German): |  Creative Commons - CC BY-NC - Namensnennung - Nicht kommerziell 4.0 International |