explainable ai

Beyond skills: Employer-perceived labour substitutability and graduate competitiveness in high-cost labour markets

This paper examines how graduates from high-cost labour markets can remain competitive amid global wage arbitrage, generative AI-enabled task transformation, and cross-border talent substitution. Using Hong Kong as a theoretically significant case, it reframes graduate employability as a problem of cost-adjusted gradua...

TD-GAE: A multimodal large language model framework for adaptive and explainable guided art learning

Findings indicate that TD-GAE can support creative learning as an adaptive, explainable, and pedagogically grounded AI tutoring framework.

Dynamic Reconstruction of Atomically Dispersed Copper Catalysts for CO 2 Reduction: From In Situ Observations to Rational Design

The electrocatalytic CO 2 reduction reaction (CO 2 RR) to useful multicarbon (C 2+ ) products offers a way to help achieve carbon neutrality. Copper‐based catalysts are uniquely capable of achieving this efficiently; however, when used as single atoms or dual‐atom pairs, their structures change significantly...

A conceptual framework for integrating digital tools into school-based psychosocial support for inclusive education in South Africa

A conceptual framework for integrating digital tools into school-based psychosocial support in South African schools was developed and showed that digital tools can extend access to psychosocial support, support task-shifting to teachers and lay providers, strengthen referral and supervision systems, and improve monito...

Development of an explainable AI model for predicting 3-month functional recovery in middle-to older-age trauma patients visiting emergency department

AI washing as a knowledge governance failure in organizations

This study aims to conceptualize AI washing as a knowledge governance failure (KGF) and develops a framework explaining how persistent symbolic AI adoption progressively undermines organizational learning, knowledge validation and capability development.

A Leakage‐Free, Patient‐Level Evaluation Protocol for Multi‐Class Lung CT Diagnosis

A systematic patient‐level evaluation protocol is offered that provides a clear and reproducible protocol aligned with CLAIM and TRIPOD+AI reporting principles, supporting more trustworthy evaluation of medical AI systems developed using multi‐slice imaging data.

Beyond Single-Modality Detection: A Systematic Review of Multimodal AI for Social Media Cybercrime

The necessity of developing a multimodal detection system that is uniform, adaptive and explainable, which can work in heterogeneous environments on social media platforms is suggested, and some research directions for achieving this goal are proposed.

From Processing to Performance: A Multi-Scale Machine Learning Framework for SBS-Modified Asphalt Gels with Multi-Target Correlation and Explainable AI

A multi-scale machine learning framework is proposed to establish processing–composition–structure–performance mappings for SBS-modified asphalt gels and enables accurate and interpretable prediction of gel properties and provides a data-driven foundation for material design.

Hybridizing AI pipelines with Ontologically Explainable Classifiers

International audience

Let Me Explain!: Explainable NLP for Understanding Large Language Models

Large Language Models (LLMs) have transformed natural language processing (NLP), but their billions of parameters make them opaque. This lack of transparency is especially problematic in high-risk areas such as healthcare, finance, and content moderation, where understanding model decisions is essential for responsible...

Are explainable AI (XAI) evaluation strategies aligned? Comparing subjective, objective, and mathematical evaluation measures using saliency maps