Carregant...
Miniatura

Tipus de document

Article

Versió

Versió publicada

Data de publicació

Llicència de publicació

cc-by-nc-nd (c) Roger Xavier Lera Leri et al., 2024
Si us plau utilitzeu sempre aquest identificador per citar o enllaçar aquest document: https://hdl.handle.net/2445/217663

Aggregating Value Systems for Decision Support

Títol de la revista

Director/Tutor

ISSN de la revista

Títol del volum

Resum

We adopt an emerging and prominent vision of human-centred Artificial Intelligence that requires building trustworthy intelligent systems. Such systems should be capable of dealing with the challenges of an interconnected globalised world by handling plurality and by abiding to human values. Within this vision, pluralistic value alignment is a core problem for AI - that is, the challenge of creating AI systems that align with a set of diverse individual value systems. So far, most literature on value-alignment has considered alignment to a single value system. To address this research gap, we propose a novel method for the estimation and aggregation of multiple individual value systems. We rely on recent results in the social choice literature and formalise the value system aggregation problem as an optimisation problem. We then cast this problem as an $\ell_p$-regression problem. By doing so, we provide a principled and general theoretical framework to model and solve the aggregation problem. Our aggregation method allows us to consider a range of ethical principles, from utilitarian (maximum utility) to egalitarian (maximum fairness). We illustrate the aggregation of value systems by considering real-world data of two case studies: the Participatory Value Evaluation process, and the European Values Study. Our experimental evaluation shows how different consensus value systems can be obtained depending on the ethical principle of choice, leading to practical insights for a decision-maker on how to perform value system aggregation.

Citació

Citació

LERA LERI, Roger xavier, LISCIO, Enrico, BISTAFFA, Filippo, JONKER, Catholijn maria, LÓPEZ SÁNCHEZ, Maite, MURUKANNAIAH, Pradeep kumar, RODRÍGUEZ AGUILAR, Juan antonio, SALAS MOLINA, Francisco. Aggregating Value Systems for Decision Support. _Knowledge-Based Systems_. 2024. Vol. 287. [consulta: 20 de gener de 2026]. ISSN: 0950-7051. [Disponible a: https://hdl.handle.net/2445/217663]

Exportar metadades

JSON - METS

Compartir registre