Human Values in Multiagent Systems
This work addresses the problem of ethical AI alignment for developers and researchers, but it is incremental as it focuses on formalizing values rather than implementing solutions.
The paper tackles the challenge of aligning AI behavior with ambiguous and contradictory human values by proposing a formal representation grounded in social sciences, and it outlines key challenges and a research roadmap for achieving value-aligned behavior in multiagent systems.
One of the major challenges we face with ethical AI today is developing computational systems whose reasoning and behaviour are provably aligned with human values. Human values, however, are notorious for being ambiguous, contradictory and ever-changing. In order to bridge this gap, and get us closer to the situation where we can formally reason about implementing values into AI, this paper presents a formal representation of values, grounded in the social sciences. We use this formal representation to articulate the key challenges for achieving value-aligned behaviour in multiagent systems (MAS) and a research roadmap for addressing them.