发表机构
Swinburne University of Technology（斯威本科技大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对标准RAG系统存在的语境脱耦问题，提出TA-RAG框架，将交流对齐与事实准确性并列为核心设计目标，明确语气感知是高风险语境下RAG系统的设计要务。
AI 中文摘要
检索增强生成（RAG）已成为将大型语言模型（LLM）锚定到可信知识中的稳健架构。然而，标准RAG系统存在结构性局限：检索到的文档带有自身的交流风格——专业术语、正式语气或学术写作风格——这些会在处理任何语气指令前就影响RAG系统的行为，常导致系统忽略用户对特定语气的请求。我们将此现象称为语境脱耦，即系统在优化事实准确性的同时，与接收者的社会或操作语境脱钩。基于公共健康同伴支持社区的前期研究，我们识别出三种交流失配——语言层面、认知层面和关系层面——即使检索相关且生成的回应在事实上准确，这些失配仍可能存在。我们将这些视为交流转换的失败，这类失败在以准确性为中心的RAG评估指标中基本不可见。为解决这一差距，我们提出语气感知RAG（TA-RAG），这是一个概念性架构框架，将交流对齐与事实准确性并列为核心设计目标。TA-RAG在拟议的RAG流程的检索、语境构建、生成和约束验证阶段，实施四项约束：无污名语言、可读性对齐、接收者敏感适应和共情框架。我们还强调了联合评估事实保真度和交流对齐的评估议程，并指出未解决的挑战。我们认为，语气感知不应被视为可选的优化，而应被视为在社会敏感和高风险语境中运行的RAG系统的当前设计要务。
英文摘要
Retrieval-Augmented Generation (RAG) has become a robust architecture for grounding large language models (LLMs) in trusted knowledge. However, standard RAG systems exhibit a structural limitation: retrieved documents carry their own communication styles-professional jargon, formal tone, or academic writings-that shape the behavior of a RAG system before any tone instructions are processed, often causing the system to ignore user requests for a specific tone. We term this phenomenon contextual decoupling, in which a system optimises for factual accuracy while remaining decoupled from the social or operational context of the recipient. Building on prior research in public health peer-support communities, we identify three communicative misalignment-linguistic, cognitive, and relational-that can persist even when retrieval is relevant and the generated response is factually accurate. We conceptualise these as failures of communicative transformation, which remain largely invisible to accuracy-centred RAG evaluation metrics. To address this gap, we propose Tone-Aware RAG (TA-RAG), a conceptual architectural framework that positions communicative alignment alongside factual accuracy as a core design objective. TA-RAG operationalises four constraints-stigma-free language, readability alignment, recipient-sensitive adaptation, and empathetic framing-across the retrieval, context construction, generation, and constraint validation phases in the proposed RAG pipeline. We further highlight an evaluation agenda for jointly assessing factual fidelity and communicative alignment, and identify open challenges. We argue that tone awareness should be treated not as an optional refinement, but as a present design imperative for RAG systems operating in socially sensitive and high-stakes contexts.
