In Conversation with Artificial Intelligence: Aligning language Models with Human Values

Philosophy and Technology 36 (2):1-24 (2023)
  Copy   BIBTEX

Abstract

Large-scale language technologies are increasingly used in various forms of communication with humans across different contexts. One particular use case for these technologies is conversational agents, which output natural language text in response to prompts and queries. This mode of engagement raises a number of social and ethical questions. For example, what does it mean to align conversational agents with human norms or values? Which norms or values should they be aligned with? And how can this be accomplished? In this paper, we propose a number of steps that help answer these questions. We start by developing a philosophical analysis of the building blocks of linguistic communication between conversational agents and human interlocutors. We then use this analysis to identify and formulate ideal norms of conversation that can govern successful linguistic communication between humans and conversational agents. Furthermore, we explore how these norms can be used to align conversational agents with human values across a range of different discursive domains. We conclude by discussing the practical implications of our proposal for the design of conversational agents that are aligned with these norms and values.

Similar books and articles

Machine Ethics.Michael Anderson & Susan Leigh Anderson (eds.) - 2011 - Cambridge Univ. Press.
Does Artificial Intelligence Use Private Language?Ryan Miller - forthcoming - In Proceedings of the International Ludwig Wittgenstein Symposium 2021. Vienna: Lit Verlag.
Artificial Language Philosophy of Science.Sebastian Lutz - 2011 - European Journal for Philosophy of Science 2 (2):181–203.
Bigger Isn’t Better: The Ethical and Scientific Vices of Extra-Large Datasets in Language Models.Trystan S. Goetze & Darren Abramson - 2021 - WebSci '21: Proceedings of the 13th Annual ACM Web Science Conference (Companion Volume).
Form and content in semantics.Y. Wilks - 1990 - Synthese 82 (3):329-51.
Слово в техногенном многомерном пространстве.Д. С Быльева - 2022 - Философские Проблемы Информационных Технологий И Киберпространства 1:18-33.
Ai: Its Nature and Future.Margaret A. Boden - 2016 - Oxford University Press UK.

Analytics

Added to PP
2022-12-06

Downloads
1,036 (#11,618)

6 months
357 (#4,690)

Historical graph of downloads
How can I increase my downloads?

Author's Profile

Atoosa Kasirzadeh
University of Edinburgh

References found in this work

IX.—Essentially Contested Concepts.W. B. Gallie - 1956 - Proceedings of the Aristotelian Society 56 (1):167-198.
The Scientist Qua Scientist Makes Value Judgments.Richard Rudner - 1953 - Philosophy of Science 20 (1):1-6.
Inductive risk and values in science.Heather Douglas - 2000 - Philosophy of Science 67 (4):559-579.
Four Decades of Scientific Explanation.Wesley C. Salmon & Anne Fagot-Largeault - 1989 - History and Philosophy of the Life Sciences 16 (2):355.

View all 29 references / Add more references