RT Conference Proceedings
T1 Interpretability and the measurement of ethical foundations in artificial intelligence
A1 Houghton Torralba, Miguel
A1 Shu, Ziwei
A1 Carrasco González, Ramón Alberto
A1 Blasco López, María Francisca
A2 Isabel Alvarez, 
A2 Arias Oliva, Mario
A2 Adrian-Horia Dediu, 
A2 Nuno Silva, 
AB With the rapid development of Artificial Intelligence (AI), its integration into decision-making processes across various sectors is accelerating. The demand for interpretability and ethical accountability has become more urgent than ever. This work explores the critical intersection of these two domains. It begins by examining the concept of interpretability in AI, then turns to the ethical foundations of AI. This work also examines how these intertwined concepts of interpretability and ethics are pivotal in advancing corporate social responsibility (CSR) by fostering transparency, enabling responsible governance, and addressing societal impacts such as algorithmic bias, job displacement, and environmental concerns. Integrating interpretability and ethics is essential for building transparent, accountable, and demonstrably ethically sound AI systems that proactively support robust CSR objectives and ensure profound alignment with human values and fundamental rights. This crucial integration helps create equitable opportunities for all, paving the way for a genuinely responsible and sustainable technological future that benefits society broadly and promotes inclusive growth.
SN 978-3-032-01429-0
SN 0302-9743
YR 2026
FD 2026
LK https://hdl.handle.net/20.500.14352/131102
UL https://hdl.handle.net/20.500.14352/131102
LA eng
NO Houghton Torralba, M., Shu, Z., Carrasco, RA., Blasco López, M.F. (2026). Interpretability and the Measurement of Ethical Foundations in Artificial Intelligence. In: Alvarez, I., Arias-Oliva, M., Dediu, AH., Silva, N. (eds) Ethical and Social Impacts of Information and Communication Technology. ETHICOMP 2025. Lecture Notes in Computer Science, vol 15939. Springer, Cham. https://doi.org/10.1007/978-3-032-01429-0_3
NO Facultad de Estudios Estadísticos. Universidad Complutense de Madrid
DS Docta Complutense
RD 31 ene 2026