EmoStage：一种通过视角采择与阶段识别实现准确共情回复生成的框架
EmoStage: A Framework for Accurate Empathetic Response Generation via Perspective-Taking and Phase Recognition
AI总结：
EmoStage利用开源大模型推理能力，通过视角采择与阶段识别增强共情回复生成，无需额外训练数据，在日中文咨询场景中提升回复质量并媲美数据驱动方法。
摘要：
心理健康护理需求的日益增长推动了人们对人工智能驱动的咨询系统的兴趣。尽管大型语言模型（LLMs）提供了巨大的潜力，但当前的方法仍面临诸多挑战，包括对来访者心理状态和咨询阶段的理解有限、依赖高质量训练数据，以及与商业部署相关的隐私问题。为解决这些问题，我们提出了EmoStage，一个通过利用开源LLMs的推理能力来增强共情回复生成的框架，无需额外的训练数据。我们的框架引入了视角采择（perspective-taking）来推断来访者的心理状态和支持需求，从而生成情感共鸣的回复。此外，框架还融入了阶段识别（phase recognition），以确保回复与咨询过程保持一致，并防止出现情境不适当或不合时宜的回复。在日语和中文咨询场景中进行的实验表明，EmoStage提升了基础模型生成的回复质量，并与数据驱动方法表现相当。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
