用大模型模拟家庭对话，识别家长隐性偏见并生成共情反馈。
Role-Playing LLM-Based Multi-Agent Support Framework for Detecting and Addressing Family Communication Bias
- 构建亲子对话数据集，通过多智能体分析情绪抑制与理想父母偏见。
- 检测到情绪压抑类别准确率中等，反馈在共情与实用性上获高分。
- 适合家庭教育咨询、心理干预研究者使用，可辅助改善亲子沟通。
家庭福祉涉及微妙的心理动态，传统指标常忽略此类问题。尤其无意识的家长期望（称作理想父母偏见）会抑制孩子的表达自由与情感自主。这种抑制被称为情绪压抑，往往源于善意但带有价值导向的沟通，外部难以察觉或干预。本研究聚焦这些潜在互动模式，探索基于大语言模型（LLM）的家庭沟通支持框架。我们构建了包含30个场景的日本亲子对话语料库，并标注了理想父母偏见与情绪压抑信息。在此基础上，开发了一个基于角色扮演的多智能体对话支持系统：专门智能体检测情绪压抑，揭示家长话语中的隐性理想父母偏见，并推断孩子年龄与背景等上下文特征；元智能体整合输出形成结构化报告，再交由五名专家智能体，通过四步结构化讨论流程协作生成共情且可操作的反馈。实验表明，系统能以中等准确率识别情绪压抑类别，反馈在共情与实用性方面评分较高。模拟后续对话显示情绪表达与相互理解有所提升，表明该框架在促进家庭关系积极转变方面具有潜力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。