Value-Aware Multiagent Systems
This addresses the challenge of making AI systems more ethically robust and interpretable for developers and users, though it appears incremental as it builds on existing value-alignment concepts.
The paper tackles the problem of engineering AI systems that are aware of human values beyond alignment, proposing a roadmap with three pillars: learning values via formal semantics, ensuring alignment in multiagent systems, and providing value-based explainability, with applications to real-life domains.
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.