How should AI decisions be explained? Requirements for Explanations from the Perspective of European Law

B Fresz, E Dubovitskaya, D Brajovic… - Proceedings of the …, 2024 - ojs.aaai.org
This paper investigates the relationship between law and eXplainable Artificial Intelligence
(XAI). While there is much discussion about the AI Act, which was adopted by the European …

Opening the Analogical Portal to Explainability: Can Analogies Help Laypeople in AI-assisted Decision Making?

G He, A Balayn, S Buijsman, J Yang… - Journal of Artificial …, 2024 - jair.org
Abstract Concepts are an important construct in semantics, based on which humans
understand the world with various levels of abstraction. With the recent advances in …

[HTML][HTML] The efficiency-accountability tradeoff in AI integration: Effects on human performance and over-reliance

N Spatola - Computers in Human Behavior: Artificial Humans, 2024 - Elsevier
As artificial intelligence proliferates across various sectors, it is crucial to explore the
psychological impacts of over-reliance on these systems. This study examines how different …

Integrating Evidence into the Design of XAI and AI-based Decision Support Systems: A Means-End Framework for End-users in Construction

P Love, J Matthews, W Fang… - arxiv preprint arxiv …, 2024 - arxiv.org
A narrative review is used to develop a theoretical evidence-based means-end framework to
build an epistemic foundation to uphold explainable artificial intelligence instruments so that …

Towards the new xai: A hypothesis-driven approach to decision support using evidence

T Le, T Miller, L Sonenberg, R Singh - ECAI 2024, 2024 - ebooks.iospress.nl
Prior research on AI-assisted human decision-making has explored several different
explainable AI (XAI) approaches. A recent paper has proposed a paradigm shift calling for …

A Survey of AI Reliance

S Eckhardt, N Kühl, M Dolata, G Schwabe - arxiv preprint arxiv …, 2024 - arxiv.org
Artificial intelligence (AI) systems have become an indispensable component of modern
technology. However, research on human behavioral responses is lagging behind, ie, the …

[HTML][HTML] An interdisciplinary perspective on AI-supported decision making in medicine

J Ammeling, M Aubreville, A Fritz, A Kießig, S Krügel… - Technology in …, 2025 - Elsevier
Artificial intelligence (AI)-supported medical diagnosis offers the potential to utilize the
collaborative intelligence of context-sensitive humans and narrowly focused machines for …

" I think you need help! Here's why": Understanding the Effect of Explanations on Automatic Facial Expression Recognition

S Nahulanthran, M Vered, L Tian, D Kulić - arxiv preprint arxiv …, 2024 - arxiv.org
Facial expression recognition (FER) has emerged as a promising approach to the
development of emotion-aware intelligent systems. The performance of FER in multiple …

Visual evaluative ai: A hypothesis-driven tool with concept-based explanations and weight of evidence

T Le, T Miller, R Zhang, L Sonenberg… - arxiv preprint arxiv …, 2024 - arxiv.org
This paper presents Visual Evaluative AI, a decision aid that provides positive and negative
evidence from image data for a given hypothesis. This tool finds high-level human concepts …

Towards reconciling usability and usefulness of policy explanations for sequential decision-making systems

P Tambwekar, M Gombolay - Frontiers in Robotics and AI, 2024 - frontiersin.org
Safefy-critical domains often employ autonomous agents which follow a sequential decision-
making setup, whereby the agent follows a policy to dictate the appropriate action at each …