TA-RAG: 面向同伴支持健康沟通的语气感知检索增强生成
TA-RAG: Tone-Aware Retrieval-Augmented Generation for Peer-Support Health Communication
- Swinburne University of Technology（斯winburne大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
提出TA-RAG框架，通过轻量级提示在RAG管道中嵌入语气控制（无污名化、可读性调整、受众适应、同理心改写），无需微调模型，提升敏感健康沟通质量。
AI中文摘要：
检索增强生成（RAG）成功地将大型语言模型（LLM）的输出建立在可信文档上，但仅靠事实依据不足以支持敏感的同伴健康沟通。在HIV同伴支持等领域，回复还必须易于理解、无污名化、富有同理心并针对接收者定制。本文提出TA-RAG，一个轻量级的、基于提示的语气感知RAG框架，它将明确的语气控制嵌入到RAG管道中，无需模型微调。我们通过四个核心组件来操作化语气：无污名化改写、可读性调整、接收者适应和同理心重述。我们使用来自澳大利亚HIV在线学习（HOLA）、UNAIDS术语指南、可读性指标、澳大利亚HIV感染者协会（NAPWHA）的同伴支持标准以及公共同理心数据集的问题，通过组件级测试评估TA-RAG。结果表明，TA-RAG的组件在保留关键内容的同时，提高了其目标沟通质量。这些发现强调，基于提示的语气控制是使RAG输出适用于敏感同伴支持健康沟通的一个潜在方向。
英文摘要：
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.
