Indexing is an important step towards strong performance in retrieval-augmented generation (RAG) systems. However, existing methods organize data based on either semantic similarity (similarity) or related information (relatedness), but do not cover both perspectives comprehensively. Our analysis reveals that modeling only one perspective results in insufficient knowledge synthesis, leading to suboptimal performance on complex tasks requiring multihop reasoning. In this paper, we propose SiReRAG, a novel RAG indexing approach that explicitly considers both similar and related information. On the similarity side, we follow existing work and explore some variances to construct a similarity tree based on recursive summarization. On the relatedness side, SiReRAG extracts propositions and entities from texts, groups propositions via shared entities, and generates recursive summaries to construct a relatedness tree. We index and flatten both similarity and relatedness trees into a unified retrieval pool. Our experiments demonstrate that SiReRAG consistently outperforms state-of-the-art indexing methods on three multihop datasets (MuSiQue, 2WikiMultiHopQA, and HotpotQA), with an average 1.9% improvement in F1 scores. As a reasonably efficient solution, SiReRAG enhances existing reranking methods significantly, with up to 7.8% improvement in average F1 scores.

翻译：索引是实现检索增强生成（RAG）系统高性能的重要步骤。然而，现有方法仅基于语义相似性（相似性）或相关信息（相关性）来组织数据，未能全面覆盖这两个维度。我们的分析表明，仅建模单一维度会导致知识综合不足，从而在需要多跳推理的复杂任务上表现欠佳。本文提出SiReRAG，一种新颖的RAG索引方法，明确同时考虑相似信息与相关信息。在相似性方面，我们遵循现有工作并探索若干变体，基于递归摘要构建相似性树。在相关性方面，SiReRAG从文本中提取命题与实体，通过共享实体对命题进行分组，并生成递归摘要以构建相关性树。我们将相似性树与相关性树索引并展平至统一的检索池中。实验表明，在三个多跳数据集（MuSiQue、2WikiMultiHopQA和HotpotQA）上，SiReRAG持续优于当前最先进的索引方法，F1分数平均提升1.9%。作为一种效率合理的解决方案，SiReRAG显著增强了现有重排序方法，平均F1分数最高提升达7.8%。