"I Felt Bad After We Ignored Her": Understanding How Interface-Driven Social Prominence Shapes Group Discussions with GenAI

2026-02-16

AI Summary

This study addresses the underexplored role of interface design in shaping how generative artificial intelligence (GenAI) influences group interaction within multi-party video conversations. Proposing a “interface-driven social salience” perspective, the work introduces a GenAI agent capable of participating in spoken dialogue and implements three collaborative modes to modulate its presence and user control. Through an integrated generative dialogue system, seamless video conferencing, and a mixed-methods experiment with 18 dyads in a within-subjects design, findings reveal that the social salience of GenAI significantly reshapes communication patterns, distribution of speaking turns, and collective negotiation of its influence. This research pioneers the integration of social salience into human-AI collaborative interface design, demonstrating how interface configurations shape human perceptions and interactions with AI, and culminates in design principles to support effective coordination and critical engagement in human-AI hybrid groups.

Technology Category

• Humans and AI: Intelligent User Interfaces
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction
• Multiagent Systems: Agent Communication

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Recent advancements in the conversational and social capabilities of generative AI (GenAI) have sparked interest in its role as an agent capable of actively participating in human-AI group discussions. Despite this momentum, we don't fully understand how GenAI shapes conversational dynamics or how the interface design impacts its influence on the group. In this paper, we introduce interface-driven social prominence as a design lens for collaborative GenAI systems. We then present a GenAI-based conversational agent that can actively engage in spoken dialogue during video calls and design three distinct collaboration modes that vary the social prominence of the agent by manipulating its presence in the shared space and the degree of control users have over its participation. A mixed-methods within-subjects study, in which 18 dyads engaged in realistic discussions with a GenAI agent, offers empirical insights into how communication patterns and the collective negotiation of GenAI's influence shift based on how it is embedded into the collaborative experience. Based on these findings, we outline design implications for supporting the coordination and critical engagement required in human-AI groups.

Problem

• generative AI
• social prominence
• group discussion
• interface design
• conversational dynamics

Innovation

• interface-driven social prominence
• generative AI
• collaborative systems
• conversational agent
• human-AI group interaction