TA-RAG: Tone-Aware Retrieval-Augmented Generation for Peer-Support Health Communication
Quick Answer
TA-RAG is a novel tone-aware retrieval-augmented generation framework designed for sensitive peer-support health communication, particularly in HIV contexts.
Quick Take
TA- is a novel tone-aware retrieval-augmented generation framework designed for sensitive peer-support health communication, particularly in HIV contexts. It incorporates stigma-free rewriting, readability adjustments, recipient adaptation, and empathy rephrasing without requiring model fine-tuning. Evaluations show improved communication quality while maintaining essential content.
Key Points
- TA-RAG embeds tone control in RAG without model fine-tuning.
- Framework operationalizes tone through four core components.
- Evaluated using HIV Online Learning Australia and empathy datasets.
- Results indicate improved communication quality for sensitive topics.
- Focuses on stigma-free, empathetic, and tailored responses.
Article Content
From source RSS / original summaryarXiv:2606. 06794v1 Announce Type: new Abstract: (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.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CL
See more →Time to REFLECT: Can We Trust LLM Judges for Evidence-based Research Agents?
The REFLECT benchmark reveals that current LLM judges are unreliable, achieving below 55% accuracy in evaluating reasoning and evidence use, highlighting the need for improved evaluation methods for deep research agents.