Participation Interfaces for Human-Centered AI

TL;DR

This paper presents interactive visual participation interfaces for AI systems, enabling diverse stakeholders to express preferences and negotiate interests, thereby promoting human-centered control in AI decision-making processes.

Contribution

It introduces novel visual interfaces for MDPs and ranking problems that facilitate stakeholder participation and negotiation in AI system design.

Findings

Interfaces support stakeholder engagement in AI decision processes

Enhance transparency and collaboration among diverse user groups

Applicable to various AI applications involving stakeholder interests

Abstract

Emerging artificial intelligence (AI) applications often balance the preferences and impacts among diverse and contentious stakeholder groups. Accommodating these stakeholder groups during system design, development, and deployment requires tools for the elicitation of disparate system interests and collaboration interfaces supporting negotiation balancing those interests. This paper introduces interactive visual "participation interfaces" for Markov Decision Processes (MDPs) and collaborative ranking problems as examples restoring a human-centered locus of control.