Investigating LLM-Powered Dissenting Minority Support in Power-Imbalanced Group Decision-Making: Counterargument and Mediation as Intervention Strategies

2026-06-30

AI Summary

This study addresses the suppression of minority viewpoints in group decision-making contexts characterized by power asymmetry, where social pressure often marginalizes dissenting voices. To enhance the expression and influence of minority participants, the authors propose two large language model (LLM)-based intervention strategies: AI-generated counterarguments and AI-mediated messaging. Through a mixed-methods experimental design, they find that AI-generated counterarguments significantly improve discussion flexibility and participant satisfaction. In contrast, while AI mediation increases participation, it unexpectedly reduces psychological safety, revealing a tension between fostering engagement and maintaining a supportive interpersonal environment. These findings offer a novel design paradigm and empirical foundation for developing AI-augmented systems that promote equitable deliberation.

Abstract

Minority viewpoints are often suppressed in power-imbalanced group decision-making due to social pressure to comply with the majority. To address this problem, we developed an LLM-powered dissenting minority support system that aimed to foster attention to minority views through either AI-generated counterarguments or AI-mediated messages. We conducted a mixed-method experiment with 96 participants in 24 groups, comparing minority members' experiences across baseline, AI-counterargument, and AI-mediated message conditions. Our findings revealed a nuanced trade-off: AI-generated counterarguments fostered a more flexible atmosphere and enhanced satisfaction, while AI-mediated messaging increased minority participation but unexpectedly reduced their psychological safety. This research contributes empirical evidence on how different AI implementations affect group dynamics, identifies a critical support paradox between participation and psychological safety, provides design implications for future systems, and highlights ethical challenges in implementing AI-mediated communication in hierarchical settings. These insights advance understanding of designing more equitable AI support for power-imbalanced group decision-making.

Problem

• minority viewpoints
• power-imbalanced group decision-making
• social pressure
• psychological safety
• group dynamics

Innovation

• LLM-powered support
• minority viewpoint
• AI mediation
• group decision-making
• power imbalance