How cognitive biases affect XAI-assisted decision-making: A systematic review

A Bertrand, R Belloum, JR Eagan… - Proceedings of the 2022 …, 2022 - dl.acm.org
The field of eXplainable Artificial Intelligence (XAI) aims to bring transparency to complex AI
systems. Although it is usually considered an essentially technical field, effort has been …

Uncertainty quantification in machine learning for engineering design and health prognostics: A tutorial

V Nemani, L Biggio, X Huan, Z Hu, O Fink… - … Systems and Signal …, 2023 - Elsevier
On top of machine learning (ML) models, uncertainty quantification (UQ) functions as an
essential layer of safety assurance that could lead to more principled decision making by …

Generative AI and ChatGPT: Applications, challenges, and AI-human collaboration

F Fui-Hoon Nah, R Zheng, J Cai, K Siau… - Journal of Information …, 2023 - Taylor & Francis
Artificial intelligence (AI) has elicited much attention across disciplines and industries (Hyder
et al., 2019). AI has been defined as “a system's ability to correctly interpret external data, to …

[PDF][PDF] Ai transparency in the age of llms: A human-centered research roadmap

QV Liao, JW Vaughan - arXiv preprint arXiv:2306.01941, 2023 - assets.pubpub.org
The rise of powerful large language models (LLMs) brings about tremendous opportunities
for innovation but also looming risks for individuals and society at large. We have reached a …

Data cards: Purposeful and transparent dataset documentation for responsible ai

M Pushkarna, A Zaldivar, O Kjartansson - Proceedings of the 2022 ACM …, 2022 - dl.acm.org
As research and industry moves towards large-scale models capable of numerous
downstream tasks, the complexity of understanding multi-modal datasets that give nuance to …

Towards trustworthy machine fault diagnosis: A probabilistic Bayesian deep learning framework

T Zhou, T Han, EL Droguett - Reliability Engineering & System Safety, 2022 - Elsevier
Fault diagnosis is efficient to improve the safety, reliability, and cost-effectiveness of
industrial machinery. Deep learning has been extensively investigated in fault diagnosis …

Investigating explainability of generative AI for code through scenario-based design

J Sun, QV Liao, M Muller, M Agarwal, S Houde… - Proceedings of the 27th …, 2022 - dl.acm.org
What does it mean for a generative AI model to be explainable? The emergent discipline of
explainable AI (XAI) has made great strides in helping people understand discriminative …

Look before you leap: An exploratory study of uncertainty measurement for large language models

Y Huang, J Song, Z Wang, S Zhao, H Chen… - arXiv preprint arXiv …, 2023 - arxiv.org
The recent performance leap of Large Language Models (LLMs) opens up new
opportunities across numerous industrial applications and domains. However, erroneous …

Understanding the role of human intuition on reliance in human-AI decision-making with explanations

V Chen, QV Liao, J Wortman Vaughan… - Proceedings of the ACM …, 2023 - dl.acm.org
AI explanations are often mentioned as a way to improve human-AI decision-making, but
empirical studies have not found consistent evidence of explanations' effectiveness and, on …

Accountability in an algorithmic society: relationality, responsibility, and robustness in machine learning

AF Cooper, E Moss, B Laufer… - Proceedings of the 2022 …, 2022 - dl.acm.org
In 1996, Accountability in a Computerized Society [95] issued a clarion call concerning the
erosion of accountability in society due to the ubiquitous delegation of consequential …