A multidisciplinary survey and framework for design and evaluation of explainable AI systems

S Mohseni, N Zarei, ED Ragan - ACM Transactions on Interactive …, 2021 - dl.acm.org
The need for interpretable and accountable intelligent systems grows along with the
prevalence of artificial intelligence (AI) applications used in everyday life. Explainable AI …

Transitioning to human interaction with AI systems: New challenges and opportunities for HCI professionals to enable human-centered AI

W Xu, MJ Dainoff, L Ge, Z Gao - International Journal of Human …, 2023 - Taylor & Francis
While AI has benefited humans, it may also harm humans if not appropriately developed.
The priority of current HCI work should focus on transiting from conventional human …

[图书][B] Human-centered AI

B Shneiderman - 2022 - books.google.com
The remarkable progress in algorithms for machine and deep learning have opened the
doors to new opportunities, and some dark possibilities. However, a bright future awaits …

Bridging the gap between ethics and practice: guidelines for reliable, safe, and trustworthy human-centered AI systems

B Shneiderman - ACM Transactions on Interactive Intelligent Systems …, 2020 - dl.acm.org
This article attempts to bridge the gap between widely discussed ethical principles of Human-
centered AI (HCAI) and practical steps for effective governance. Since HCAI systems are …

DARPA's explainable artificial intelligence (XAI) program

D Gunning, D Aha - AI magazine, 2019 - ojs.aaai.org
Dramatic success in machine learning has led to a new wave of AI applications (for
example, transportation, security, medicine, finance, defense) that offer tremendous benefits …

Designing theory-driven user-centric explainable AI

D Wang, Q Yang, A Abdul, BY Lim - … of the 2019 CHI conference on …, 2019 - dl.acm.org
From healthcare to criminal justice, artificial intelligence (AI) is increasingly supporting high-
consequence human decisions. This has spurred the field of explainable AI (XAI). This …

[HTML][HTML] The explainability paradox: Challenges for xAI in digital pathology

T Evans, CO Retzlaff, C Geißler, M Kargl… - Future Generation …, 2022 - Elsevier
The increasing prevalence of digitised workflows in diagnostic pathology opens the door to
life-saving applications of artificial intelligence (AI). Explainability is identified as a critical …

A survey on artificial intelligence (ai) and explainable ai in air traffic management: Current trends and development with future research trajectory

A Degas, MR Islam, C Hurter, S Barua, H Rahman… - Applied Sciences, 2022 - mdpi.com
Air Traffic Management (ATM) will be more complex in the coming decades due to the
growth and increased complexity of aviation and has to be improved in order to maintain …

Principles of explanation in human-AI systems

ST Mueller, ES Veinott, RR Hoffman, G Klein… - arXiv preprint arXiv …, 2021 - arxiv.org
Explainable Artificial Intelligence (XAI) has re-emerged in response to the development of
modern AI and ML systems. These systems are complex and sometimes biased, but they …

From contrastive to abductive explanations and back again

A Ignatiev, N Narodytska, N Asher… - … Conference of the Italian …, 2020 - Springer
Abstract Explanations of Machine Learning (ML) models often address a question. Such
explanations can be related with selecting feature-value pairs which are sufficient for the …