让AI回复更贴心：用提示词控制语气，提升健康互助对话质量
TA-RAG: Tone-Aware Retrieval-Augmented Generation for Peer-Support Health Communication
- 通过提示词设计实现语气控制，无需微调模型
- 在HIV互助场景中提升无歧视性、可读性与共情表达
- 适合心理健康、医疗咨询等敏感领域应用
检索增强生成（RAG）虽能确保大模型输出的事实准确性，但在敏感的同伴支持型健康沟通中仍不足。以艾滋病同伴支持为例，回复还需具备无污名化、易理解、共情且适配对方的特点。本文提出TA-RAG，一种轻量级、基于提示词的语气感知RAG框架，不需模型微调即可嵌入语气控制。其核心包含四方面：去污名化重写、可读性调整、接收者适配和共情重述。我们基于HIVA在线学习项目（HOLA）、UNAIDS术语指南、可读性指标、澳大利亚人民与艾滋病协会（NAPWHA）同伴支持标准及公开共情数据集进行组件级评估。结果表明，各组件在保持关键内容的同时，显著提升了对应沟通质量。研究证明，基于提示词的语气控制是使RAG适用于敏感健康互助场景的可行路径。
原文摘要 · Abstract (English)
Retrieval-augmented generation (RAG) successfully grounds large language model (LLM) outputs in trusted documents, but factual grounding alone is insufficient for sensitive peer-support health communication. In domains such as HIV peer support, responses must also be accessible, stigma-free, empathetic, and tailored to the recipient. This paper presents TA-RAG, a lightweight, prompt-based tone-aware RAG framework that embeds explicit tone control into a RAG pipeline without requiring model fine-tuning. We operationalise tone across four core components: stigma-free rewriting, readability adjustment, recipient adaptation, and empathy rephrasing. We evaluate TA-RAG through component-level tests using questions derived from HIV Online Learning Australia (HOLA), UNAIDS terminology guidance, readability metrics, peer-support standards from National Association of People with HIV Australia (NAPWHA), and a public empathy dataset. Results show that the TA-RAG's components improve their targeted communication quality while preserving key content. These findings emphasise that prompt-based tone control is a potential direction for making RAG outputs suitable for sensitive peer-support health communication.
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。