Incentive Compatibility for AI Alignment in Sociotechnical Systems: Positions and Prospects

Author:

Zhaowei Zhang, Fengshuo Bai, Mingzhi Wang, Haoyang Ye, Chengdong Ma, Yaodong Yang

Keyword:

Computer Science, Artificial Intelligence, Artificial Intelligence (cs.AI), Computers and Society (cs.CY), Computer Science and Game Theory (cs.GT), Human-Computer Interaction (cs.HC)

journal:

date:

2024-02-20 00:00:00

Abstract

The burgeoning integration of artificial intelligence (AI) into human society brings forth significant implications for societal governance and safety. While considerable strides have been made in addressing AI alignment challenges, existing methodologies primarily focus on technical facets, often neglecting the intricate sociotechnical nature of AI systems, which can lead to a misalignment between the development and deployment contexts. To this end, we posit a new problem worth exploring: Incentive Compatibility Sociotechnical Alignment Problem (ICSAP). We hope this can call for more researchers to explore how to leverage the principles of Incentive Compatibility (IC) from game theory to bridge the gap between technical and societal components to maintain AI consensus with human societies in different contexts. We further discuss three classical game problems for achieving IC: mechanism design, contract theory, and Bayesian persuasion, in addressing the perspectives, potentials, and challenges of solving ICSAP, and provide preliminary implementation conceptions.

PDF: Incentive Compatibility for AI Alignment in Sociotechnical Systems: Positions and Prospects.pdf