SafeTalkCoach: Diversity-Driven Multi-Agent Simulation for Parent-Teen Health Conversations

TL;DR

SafeTalkCoach is a multi-agent simulation framework that generates diverse, realistic parent-teen conversations about sexual health, aiding AI research and health communication practices.

Contribution

It introduces a novel diversity-driven multi-agent dialogue system and dataset for sensitive health conversations, addressing realism and diversity challenges in LLMs.

Findings

Generates diverse and realistic conversations

Maintains communication quality and controllability

Supports AI research and health communication

Abstract

The importance of effective parent-child communication about sexual health is widely acknowledged, but real-world data on these conversations is scarce and challenging to collect, due to their private and sensitive nature. Although LLMs have been widely adopted in dialogue generation, they may deviate from best practices and frequently lack realism and diversity. We introduce SafeTalkCoach, a diversity-driven multi-agent dialogue generation framework that simulates parent-child conversations about sexual health, and present an accompanying dataset. SafeTalkCoach integrates crowd-sourced and synthesized scenarios, established sexual health guidelines, evidence-based personas, adaptive control modules, and hierarchical diversification. Through evaluations, we demonstrate that SafeTalkCoach generates diverse conversations while maintaining realism, communication quality, and controllability in practice. Our goal is that the SafeTalkCoach framework and the dataset support both AI research and health communications practices.