Retrieval-Augmented Generation (RAG) has emerged as an important means of enhancing the performance of large language models (LLMs) in knowledge-intensive tasks. However, most existing RAG strategies treat retrieved passages in a flat and unstructured way, which prevents the model from capturing structural cues and constrains its ability to synthesize knowledge from dispersed evidence across documents. To overcome these limitations, we propose Disco-RAG, a discourse-aware framework that explicitly injects discourse signals into the generation process. Our method constructs intra-chunk discourse trees to capture local hierarchies and builds inter-chunk rhetorical graphs to model cross-passage coherence. These structures are jointly integrated into a planning blueprint that conditions the generation. Experiments on question answering and long-document summarization benchmarks show the efficacy of our approach. Disco-RAG achieves state-of-the-art results on the benchmarks without fine-tuning. These findings underscore the important role of discourse structure in advancing RAG systems.

翻译：检索增强生成（RAG）已成为提升大型语言模型在知识密集型任务中性能的重要手段。然而，现有的大多数RAG策略以扁平化、非结构化的方式处理检索到的文本段落，这阻碍了模型捕捉结构线索，并限制了其综合来自不同文档中分散证据的能力。为了克服这些局限性，我们提出了Disco-RAG，这是一个具备篇章感知能力的框架，它显式地将篇章信号注入到生成过程中。我们的方法通过构建块内篇章树来捕捉局部层次结构，并构建块间修辞图来建模跨段落连贯性。这些结构被共同整合到一个规划蓝图中，用于指导生成过程。在问答和长文档摘要基准测试上的实验证明了我们方法的有效性。Disco-RAG在不进行微调的情况下，在这些基准测试上取得了最先进的结果。这些发现强调了篇章结构在推进RAG系统发展中的重要作用。