TA-RAG: Tone-Aware Retrieval-Augmented Generation for Peer-Support Health Communication

2026-06-04

AI Summary

This study addresses a critical limitation of traditional retrieval-augmented generation (RAG) in peer health support contexts, where systems prioritize factual accuracy while neglecting essential stylistic dimensions such as readability, destigmatization, empathy, and audience adaptation. To bridge this gap, the authors propose a lightweight, prompt-driven, tone-aware RAG framework that integrates four key components—destigmatizing rewriting, readability optimization, audience adaptation, and empathetic restatement—into the RAG pipeline without requiring model fine-tuning. Experimental results demonstrate that each component significantly enhances its targeted tonal quality while preserving core informational content. This work provides the first empirical validation that prompt engineering alone can effectively and feasibly orchestrate multidimensional tone control in sensitive health communication scenarios.

Abstract

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.

Problem

• peer-support health communication
• tone-aware
• stigma-free
• empathy
• readability

Innovation

• Tone-Aware RAG
• Prompt-Based Control
• Stigma-Free Communication
• Empathetic Rewriting
• Peer-Support Health Communication