Conversational Agents as Catalysts for Critical Thinking: Challenging Social Influence in Group Decision-making

2025-03-18

AI Summary

Power imbalances in group decision-making foster conformity and groupthink, suppressing minority viewpoints. This paper proposes and empirically validates an LLM-driven conversational “devil’s advocate” system that, through real-time, multi-turn dialogue, generates contextually appropriate, fluent counter-arguments using role-based strategies—thereby actively modulating social influence without undermining group cohesion. In a controlled experiment with 48 participants across 12 groups, AI intervention significantly increased psychological safety, expressive freedom, and process/outcome satisfaction among low-power members, enhanced viewpoint diversity, and imposed no additional cognitive load. This study provides the first empirical evidence that lightweight, context-aware LLM-based rebuttal interventions can effectively mitigate the adverse effects of power asymmetry on collective decision quality—establishing a novel paradigm for AI-augmented equitable collaboration.

Technology Category

• Humans and AI: Voting
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Group decision-making processes frequently suffer when social influence and power dynamics suppress minority viewpoints, leading to compliance and groupthink. Conversational agents can counteract these harmful dynamics by encouraging critical thinking. This study investigates how LLM-powered devil's advocate systems affect psychological safety, opinion expression, and satisfaction in power-imbalanced group dynamics. We conducted an experiment with 48 participants in 12 four-person groups, each containing three high-power (senior) and one low-power (junior) member. Each group completed decision tasks in both baseline and AI intervention conditions. Results show AI counterarguments fostered a more flexible atmosphere and significantly enhanced both process and outcome satisfaction for all participants, with particularly notable improvements for minority members. Cognitive workload increased slightly, though not significantly. This research contributes empirical evidence on how AI systems can effectively navigate power hierarchies to foster more inclusive decision-making environments, highlighting the importance of balancing intervention frequency, maintaining conversational flow, and preserving group cohesion.

Problem

• Addresses suppression of minority viewpoints in group decision-making.
• Explores AI's role in enhancing critical thinking and psychological safety.
• Investigates AI impact on satisfaction and opinion expression in power-imbalanced groups.

Innovation

• LLM-powered devil's advocate systems
• Enhance psychological safety and satisfaction
• Balance intervention frequency and group cohesion