Relational AI: Facilitating Intergroup Cooperation with Socially Aware Conversational Support

Cooperation is challenging when group identities are involved. While people readily cooperate with in-group members, they struggle to build trust with out-group members. This study examines how text suggestions generated by Large Language Models (LLMs) can mitigate in-group-out-group bias and facilitate intergroup cooperation through conversations. We conducted an experiment with 482 participants who communicated with either in-group partners sharing their views or out-group partners with differing views, based on a preliminary survey. Participants received either “personalized” message suggestions aligned with their own views and conversation styles or “relational” suggestions using conversation styles tailored to whether their partner was in-group or out-group. Following the conversations, participants engaged in a cooperation game designed to measure trust behaviorally. Our results show that while personalized assistance widened the cooperation gap, relational assistance significantly improved out-group cooperation to match in-group levels. We discuss design implications for integrating social awareness into AI-driven conversational support systems.