Addressing the Value Alignment Problem Through Online Institutions
As artificial intelligence systems permeate society, it becomes clear that aligning the behaviour of these systems with the values of those involved and affected by them is needed. The value alignment problem is widely recognised yet needs addressing in a principled way. This paper investigates how such a principled approach regarding online institutions—a class of multiagent systems—can provide key insights on how the value alignment problem can be addressed in general.
Item Type | Conference or Workshop Item (Paper) |
---|---|
Additional Information |
Research for his paper is supported by the EU Project VALAWAI 101070930 (funded by HORIZON-EIC-2021-PATHFINDERCHALLENGES-01), project VAE (grant TED2021-131295B-C31 funded by MCIN/AEI /10.13039/501100011033 and by the European Union’s NextGenerationEU/PRTR), and CSIC’s project DESAFIA2030 (BILTC22005 funded by the Bilateral Collaboration Initiative i-LINK-TEC). |
Keywords | Engineering values, Value alignment, Online institutions, WIT design pattern, Conscientious design |
Departments, Centres and Research Units | Computing |
Date Deposited | 09 Jan 2024 15:49 |
Last Modified | 20 Dec 2024 02:26 |
-
picture_as_pdf - COM-d’Inverno2023a.pdf
-
subject - Accepted Version