{"ID":5443792,"CreatedAt":"2026-07-01T02:07:11.383974684Z","UpdatedAt":"2026-07-03T14:41:59.01997188Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.31762","arxiv_id":"2606.31762","title":"Investigating LLM-Powered Dissenting Minority Support in Power-Imbalanced Group Decision-Making: Counterargument and Mediation as Intervention Strategies","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.","short_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...","url_abs":"https://arxiv.org/abs/2606.31762","url_pdf":"https://arxiv.org/pdf/2606.31762v1","authors":"[\"Soohwan Lee\",\"Seoyeong Hwang\",\"Mingyu Kim\",\"Dajung Kim\",\"Kyungho Lee\"]","published":"2026-06-30T14:50:50Z","proceeding":"cs.HC","tasks":"[\"cs.HC\"]","methods":"[\"Large Language Model\"]","has_code":false}