.png){kind=icon}
返回
Aggregating value systems for decision support
.png){kind=icon}
OA
AI
DOI：10.1016/j.knosys.2024.111453.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
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 by 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 estimating and aggregating 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 l(p)-regression problem. Doing so provides 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 from 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.
Keyword:
AI & ethics
Value systems
Optimisation
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
K
IF:
7.6
论文数:
1.2W
被引数:
4.5W
机构
引用论文
Accuracy of genome-wide imputation of untyped markers and impacts on statistical power for association studies.png)
BMC GeneticsOAAI
BMC GeneticsIF0
OAAI分享收藏Analysis and manufacture of an energy harvester based on a Mooney-Rivlin–type dielectric elastomer
PREAI
分享收藏Children With In Utero Cocaine Exposure Do Not Differ From Control Subjects on Intelligence Testing
PREAI
分享收藏When Digital Mass Participation Meets Citizen Deliberation: Combining Mini- and Maxi-Publics in Climate Policy-MakingSUSTAINABILITY
OAAI
SUSTAINABILITYIF3.3
OAAI分享收藏分享收藏
查看更多内容