TL;DR
This paper proposes a framework for developing value-aware multiagent systems that learn, represent, and explain human values to improve alignment and transparency in AI.
Contribution
It introduces the concept of value awareness in AI, outlining a roadmap with three core pillars for engineering value-aware systems and presenting initial work and applications.
Findings
Framework for learning and representing human values
Methods for ensuring value alignment in multiagent systems
Applications demonstrating value-aware AI in real-world domains
Abstract
This paper introduces the concept of value awareness in AI, which goes beyond the traditional value-alignment problem. Our definition of value awareness presents us with a concise and simplified roadmap for engineering value-aware AI. The roadmap is structured around three core pillars: (1) learning and representing human values using formal semantics, (2) ensuring the value alignment of both individual agents and multiagent systems, and (3) providing value-based explainability on behaviour. The paper presents a selection of our ongoing work on some of these topics, along with applications to real-life domains.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsExplainable Artificial Intelligence (XAI) · Ethics and Social Impacts of AI · Semantic Web and Ontologies