AI Alignment Dialogues: An Interactive Approach to AI Alignment in Support Agents

Pei Yu Chen*

*Corresponding author for this work

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

41 Downloads (Pure)

Abstract

This project proposes a different way of looking at AI alignment, namely by introducing AI Alignment Dialogues. We argue that alignment dialogues have a number of advantages in comparison to data-driven approaches, especially for behaviour support agents, which aim to support users in achieving their desired future behaviours rather than their current behaviours. The advantages of alignment dialogues include allowing the users to directly convey higher-level concepts to the agent and making the agent more transparent and trusted.

Original languageEnglish
Title of host publicationAIES 2022 - Proceedings of the 2022 AAAI/ACM Conference on AI, Ethics, and Society
PublisherAssociation for Computing Machinery (ACM)
Pages894
Number of pages1
ISBN (Electronic)978-1-4503-9247-1
DOIs
Publication statusPublished - 2022
Event5th AAAI/ACM Conference on Artificial Intelligence, Ethics, and Society, AIES 2022 - Oxford, United Kingdom
Duration: 1 Aug 20223 Aug 2022

Publication series

NameAIES 2022 - Proceedings of the 2022 AAAI/ACM Conference on AI, Ethics, and Society

Conference

Conference5th AAAI/ACM Conference on Artificial Intelligence, Ethics, and Society, AIES 2022
Country/TerritoryUnited Kingdom
CityOxford
Period1/08/223/08/22

Keywords

  • AI alignment
  • behaviour support agent
  • conversational agent
  • human values
  • responsible AI

Fingerprint

Dive into the research topics of 'AI Alignment Dialogues: An Interactive Approach to AI Alignment in Support Agents'. Together they form a unique fingerprint.

Cite this