Inferring Values via Hybrid Intelligence

Enrico Liscio*, Roger Lera-Leri, Filippo Bistaffa, Roel I.J. Dobbe, Catholijn M. Jonker, Maite Lopez-Sanchez, Juan A. Rodriguez-Aguilar, Pradeep K. Murukannaiah

*Corresponding author for this work

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

44 Downloads (Pure)

Abstract

Values, such as freedom and safety, are the core motivations that guide us humans. A prerequisite for creating value-aligned multiagent systems that involve humans and artificial agents is value inference, the process of identifying values and reasoning about human value preferences. We introduce a framework that connects the value inference steps, and motivate why a hybrid intelligence approach is instrumental for its success. We also highlight the multidisciplinary research challenges that hybrid value inference entails.

Original languageEnglish
Title of host publicationHHAI 2023
Subtitle of host publicationAugmenting Human Intellect - Proceedings of the 2nd International Conference on Hybrid Human-Artificial Intelligence
EditorsPaul Lukowicz, Sven Mayer, Janin Koch, John Shawe-Taylor, Ilaria Tiddi
PublisherIOS Press
Pages373-378
Number of pages6
ISBN (Electronic)9781643683942
DOIs
Publication statusPublished - 2023
Event2nd International Conference on Hybrid Human-Artificial Intelligence, HHAI 2023 - Munich, Germany
Duration: 26 Jun 202330 Jun 2023

Publication series

NameFrontiers in Artificial Intelligence and Applications
Volume368
ISSN (Print)0922-6389
ISSN (Electronic)1879-8314

Conference

Conference2nd International Conference on Hybrid Human-Artificial Intelligence, HHAI 2023
Country/TerritoryGermany
CityMunich
Period26/06/2330/06/23

Keywords

  • ethics
  • hybrid intelligence
  • norms
  • sociotechnical systems
  • values

Fingerprint

Dive into the research topics of 'Inferring Values via Hybrid Intelligence'. Together they form a unique fingerprint.

Cite this