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

2025-02-10

AI Summary

Power imbalances in group decision-making often suppress minority voices, undermining decision quality and inclusivity. To address this, we propose an anonymized AI advocacy mechanism: a multi-agent system grounded in large language models—comprising summarization, dialogue, paraphrasing, and AI-repetition detection agents—that dynamically simulates and articulates underrepresented perspectives without revealing participants’ identities, effectively serving as a “digital devil’s advocate.” Integrating persuasive communication strategies with privacy-preserving design, the mechanism actively fosters viewpoint diversity and enhances psychological safety in asymmetric power settings. Empirical evaluation demonstrates significant improvements in group critical thinking, reduced idea redundancy, increased willingness to express minority opinions, and heightened decision inclusivity. Our key contribution is the first AI-mediated paradigm that simultaneously ensures identity anonymity and faithful representation of diverse viewpoints.

Technology Category

• Humans and AI: Voting
• Multiagent Systems: Mechanism Design
• Philosophy and Ethics of AI: Bias, Fairness & Equity

Application Category

• Economics, Online Markets and Human Computation: Fairness, privacy, and diversity in economic environments
• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization
• Responsible Web: Machine-in-the-loop, human agency and autonomy

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.

Problem

• AI representing minority viewpoints
• Enhancing inclusive group decision-making
• Improving psychological safety in discussions

Innovation

• AI-mediated communication system
• Large Language Model advocate
• Multi-agent architecture design