通过视角转换与阶段识别，让AI更懂用户情绪和咨询阶段。
EmoStage: A Framework for Accurate Empathetic Response Generation via Perspective-Taking and Phase Recognition
- 用视角转换推断用户心理状态与支持需求
- 结合咨询阶段识别，避免不恰当回应
- 无需额外训练数据，适合隐私敏感场景
心理健康需求上升推动了人工智能辅助心理咨询系统的发展。尽管大语言模型（LLMs）具有潜力，现有方法仍面临对用户心理状态和咨询阶段理解不足、依赖高质量训练数据以及商业部署中的隐私风险等问题。为此，我们提出EmoStage框架，利用开源LLMs的推理能力，在无需额外训练数据的前提下提升共情响应生成质量。该框架引入视角转换机制以推断用户心理状态与支持需求，实现情感共鸣回应；同时集成阶段识别模块，确保回应与咨询流程一致，避免情境不当或不合时宜的回复。在日文与中文咨询场景下的实验表明，EmoStage显著提升了基线模型的响应质量，并达到与数据驱动方法相当的性能。
原文摘要 · Abstract (English)
The rising demand for mental health care has fueled interest in AI-driven counseling systems. While large language models (LLMs) offer significant potential, current approaches face challenges, including limited understanding of clients' psychological states and counseling stages, reliance on high-quality training data, and privacy concerns associated with commercial deployment. To address these issues, we propose EmoStage, a framework that enhances empathetic response generation by leveraging the inference capabilities of open-source LLMs without additional training data. Our framework introduces perspective-taking to infer clients' psychological states and support needs, enabling the generation of emotionally resonant responses. In addition, phase recognition is incorporated to ensure alignment with the counseling process and to prevent contextually inappropriate or inopportune responses. Experiments conducted in both Japanese and Chinese counseling settings demonstrate that EmoStage improves the quality of responses generated by base models and performs competitively with data-driven methods.
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。