Print Email Facebook Twitter AI Alignment Dialogues Title AI Alignment Dialogues: An Interactive Approach to AI Alignment in Support Agents Author Chen, P.Y. (TU Delft Interactive Intelligence) Date 2022 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. Subject AI alignmentbehaviour support agentconversational agenthuman valuesresponsible AI To reference this document use: http://resolver.tudelft.nl/uuid:5ecc583b-6de6-4f8f-963f-074ef87dbb8b DOI https://doi.org/10.1145/3514094.3539531 Publisher Association for Computing Machinery (ACM) ISBN 978-1-4503-9247-1 Source AIES 2022 - Proceedings of the 2022 AAAI/ACM Conference on AI, Ethics, and Society Event 5th AAAI/ACM Conference on Artificial Intelligence, Ethics, and Society, AIES 2022, 2022-08-01 → 2022-08-03, Oxford, United Kingdom Series AIES 2022 - Proceedings of the 2022 AAAI/ACM Conference on AI, Ethics, and Society Part of collection Institutional Repository Document type conference paper Rights © 2022 P.Y. Chen Files PDF 3514094.3539531.pdf 824.39 KB Close viewer /islandora/object/uuid:5ecc583b-6de6-4f8f-963f-074ef87dbb8b/datastream/OBJ/view