Role-Playing LLM-Based Multi-Agent Support Framework for Detecting and Addressing Family Communication Bias

TL;DR

This paper presents a novel LLM-based multi-agent framework that analyzes family dialogues to detect unconscious biases and suppressed emotions, providing empathetic feedback to promote healthier communication and emotional expression.

Contribution

It introduces a multi-agent system utilizing LLMs to identify implicit biases and emotions in family conversations, a new approach for supporting psychologically safe family communication.

Findings

Detects suppressed emotions with moderate accuracy

Provides feedback rated high in empathy and practicality

Simulated dialogues show improved emotional expression

Abstract

Well-being in family settings involves subtle psychological dynamics that conventional metrics often overlook. In particular, unconscious parental expectations, termed ideal parent bias, can suppress children's emotional expression and autonomy. This suppression, referred to as suppressed emotion, often stems from well-meaning but value-driven communication, which is difficult to detect or address from outside the family. Focusing on these latent dynamics, this study explores Large Language Model (LLM)-based support for psychologically safe family communication. We constructed a Japanese parent-child dialogue corpus of 30 scenarios, each annotated with metadata on ideal parent bias and suppressed emotion. Based on this corpus, we developed a Role-Playing LLM-based multi-agent dialogue support framework that analyzes dialogue and generates feedback. Specialized agents detect suppressed emotion, describe implicit ideal parent bias in parental speech, and infer contextual attributes such as the child's age and background. A meta-agent compiles these outputs into a structured report, which is then passed to five selected expert agents. These agents collaboratively generate empathetic and actionable feedback through a structured four-step discussion process. Experiments show that the system can detect categories of suppressed emotion with moderate accuracy and produce feedback rated highly in empathy and practicality. Moreover, simulated follow-up dialogues incorporating this feedback exhibited signs of improved emotional expression and mutual understanding, suggesting the framework's potential in supporting positive transformation in family interactions.