ArXiv TLDR

GroupEnvoy: A Conversational Agent Speaking for the Outgroup to Foster Intergroup Relations

🐦 Tweet
2604.16095

Koken Hata, Rintaro Chujo, Reina Takamatsu, Wenzhen Xu, Yukino Baba

cs.HC

TLDR

GroupEnvoy, an AI agent, improves intergroup relations by representing outgroup perspectives, reducing anxiety and boosting perspective-taking.

Key contributions

  • Introduces GroupEnvoy, an AI agent that voices outgroup perspectives during ingroup discussions.
  • Experimental study showed GroupEnvoy reduced intergroup anxiety and improved perspective-taking in students.
  • AI-mediated contact enhanced outcome expectancies, while passive exposure fostered future contact intentions.
  • Validates AI-mediated contact as a promising paradigm for improving intergroup relations.

Why it matters

This paper introduces a novel AI-mediated approach to foster intergroup relations, addressing barriers to direct interaction. By demonstrating GroupEnvoy's effectiveness in reducing anxiety and improving perspective-taking, it offers a practical tool for promoting understanding. The findings highlight the potential of conversational agents to bridge divides and enhance social cohesion.

Original Abstract

Conversational agents have the potential to support intergroup relations when psychological or linguistic barriers prevent direct interaction. Based on intergroup contact theory, we propose GroupEnvoy, a conversational agent that represents outgroup perspectives during ingroup discussions, grounded in transcripts from outgroup-only sessions. To evaluate this approach and derive design principles, we conducted a mixed-methods, between-subjects study with university students, where host-country students formed the ingroup and international students formed the outgroup. Ingroup students performed a collaborative task, receiving outgroup perspectives via GroupEnvoy (experimental) or reading written transcripts (control). Compared to the control group, the experimental group showed greater reduction in intergroup anxiety and greater improvement in perspective-taking. Qualitatively, AI-mediated contact enhanced outcome expectancies, whereas passive exposure fostered future contact intentions. The two conditions also elicited empathy toward distinct targets: outgroup evaluations of the ingroup versus outgroup lived experiences. These findings validate AI-mediated contact as a promising paradigm for improving intergroup relations.

📬 Weekly AI Paper Digest

Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.