STELA: a community-centred approach to norm elicitation for AI alignment
Authors:
Open Access
- 19 March 2024
- journal article
- research article
- Published by Springer Nature in Scientific Reports
- Vol. 14 (1) , 1-14
Abstract
Value alignment, the process of ensuring that artificial intelligence (AI) systems are aligned with human values and goals, is a critical issue in AI research. Existing scholarship has mainly studied how to encode moral values into agents to guide their behaviour. Less attention has been given to the normative questions of whose values and norms AI systems should be aligned with, and how these choices should be made. To tackle these questions, this paper presents the STELA process (SocioTEchnical Language agent Alignment), a methodology resting on sociotechnical traditions of participatory, inclusive, and community-centred processes. For STELA, we conduct a series of deliberative discussions with four historically underrepresented groups in the United States in order to understand their diverse priorities and concerns when interacting with AI systems. The results of our research suggest that community-centred deliberation on the outputs of large language models is a valuable tool for eliciting latent normative perspectives directly from differently situated groups. In addition to having the potential to engender an inclusive process that is robust to the needs of communities, this methodology can provide rich contextual insights for AI alignment.Keywords
This publication has 64 references indexed in Scilit:
- Role play with large language modelsNature, 2023
- Artificial Intelligence, Values, and AlignmentMinds and Machines, 2020
- The Whiteness of AIPhilosophy & Technology, 2020
- Norms and Beliefs: How Change Occurs2014
- The Moral Status of Technical Artefacts2014
- Rules of Skill: Ethics in Engineering2013
- The Sociology of Community Connections2011
- Experimenting with a Democratic Ideal: Deliberative Polling and Public OpinionActa Politica, 2005
- Using Focus Groups to Facilitate Culturally Anchored Research2002
- The origins and practice of participatory rural appraisalWorld Development, 1994