Amplifying Minority Voices: AI-Mediated Devil's Advocate System for Inclusive Group Decision-Making

Abstract

Group decision-making often benefits from diverse perspectives, yet power imbalances and social influence can stifle minority opinions and compromise outcomes. This prequel introduces an AI-mediated communication system that leverages the Large Language Model to serve as a devil's advocate, representing underrepresented viewpoints without exposing minority members' identities. Rooted in persuasive communication strategies and anonymity, the system aims to improve psychological safety and foster more inclusive decision-making. Our multi-agent architecture, which consists of a summary agent, conversation agent, AI duplicate checker, and paraphrase agent, encourages the group's critical thinking while reducing repetitive outputs. We acknowledge that reliance on text-based communication and fixed intervention timings may limit adaptability, indicating pathways for refinement. By focusing on the representation of minority viewpoints anonymously in power-imbalanced settings, this approach highlights how AI-driven methods can evolve to support more divergent and inclusive group decision-making.

10 pages, 3 figures. This is a preprint version of the poster accepted to ACM Conference on Intelligent User Interfaces(IUI'25)

References in corpus (11)

• To Trust or to Think: Cognitive Forcing Functions Can Reduce Overreliance on AI in AI-assisted Decision-making
• Designing for Responsible Trust in AI Systems: A Communication Perspective
• Competent but Rigid: Identifying the Gap in Empowering AI to Participate Equally in Group Decision-Making
• Controlling AI Agent Participation in Group Conversations: A Human-Centered Approach
• Learning Multi-Party Turn-Taking Models from Dialogue Logs
• Multi-Party Chat: Conversational Agents in Group Settings with Humans and Models
• Beyond Recommender: An Exploratory Study of the Effects of Different AI Roles in AI-Assisted Decision Making
• Silencing the Risk, Not the Whistle: A Semi-automated Text Sanitization Tool for Mitigating the Risk of Whistleblower Re-Identification
• Human-in-the-loop or AI-in-the-loop? Automate or Collaborate?
• Proactive Conversational Agents with Inner Thoughts
• Breaking Barriers or Building Dependency? Exploring Team-LLM Collaboration in AI-infused Classroom Debate