What values should an agent align with? An empirical comparison of general and context-specific values

Research output: Contribution to journalArticleScientificpeer-review

5 Citations (Scopus)
24 Downloads (Pure)

Abstract

The pursuit of values drives human behavior and promotes cooperation. Existing research is focused on general values (e.g., Schwartz) that transcend contexts. However, context-specific values are necessary to (1) understand human decisions, and (2) engineer intelligent agents that can elicit and align with human values. We propose Axies, a hybrid (human and AI) methodology to identify context-specific values. Axies simplifies the abstract task of value identification as a guided value annotation process involving human annotators. Axies exploits the growing availability of value-laden text corpora and Natural Language Processing to assist the annotators in systematically identifying context-specific values. We evaluate Axies in a user study involving 80 human subjects. In our study, six annotators generate value lists for two timely and important contexts: Covid-19 measures and sustainable Energy. We employ two policy experts and 72 crowd workers to evaluate Axies value lists and compare them to a list of general (Schwartz) values. We find that Axies yields values that are (1) more context-specific than general values, (2) more suitable for value annotation than general values, and (3) independent of the people applying the methodology.
Original languageEnglish
Article number23
Pages (from-to)1-32
Number of pages32
JournalAutonomous Agents and Multi-Agent Systems
Volume36
Issue number1
DOIs
Publication statusPublished - 2022

Keywords

  • Values
  • Ethics
  • Schwartz
  • Context
  • Axies
  • NLP

Fingerprint

Dive into the research topics of 'What values should an agent align with? An empirical comparison of general and context-specific values'. Together they form a unique fingerprint.

Cite this