针对需要整合大量文档的复杂问题，S-RAG通过结构化索引提升回答准确率。
Structured RAG for Answering Aggregative Questions
- 在数据摄入阶段构建文档结构化表示，支持复杂查询
- 在新数据集上比传统RAG和长上下文模型高出27%以上准确率
- 适合处理需跨多文档聚合信息的开放域问答场景
检索增强生成（RAG）已成为大规模语料库问答的主流方法。然而，当前的数据集与方法主要集中于单个查询仅需少量相关段落的情况，难以应对需要从大量文档中收集信息并进行推理的聚合型问题。为此，我们提出S-RAG，一种专为这类问题设计的方法。在数据摄入阶段，S-RAG构建语料库的结构化表示；在推理阶段，将自然语言问题转化为对该表示的正式查询。为验证该方法并推动该领域研究，我们引入两个新的聚合型问题数据集：HOTELS和WORLD CUP。在新数据集及公开基准上的实验表明，S-RAG显著优于常见的RAG系统和长上下文大模型。
原文摘要 · Abstract (English)
Retrieval-Augmented Generation (RAG) has become the dominant approach for answering questions over large corpora. However, current datasets and methods are highly focused on cases where only a small part of the corpus (usually a few paragraphs) is relevant per query, and fail to capture the rich world of aggregative queries. These require gathering information from a large set of documents and reasoning over them. To address this gap, we propose S-RAG, an approach specifically designed for such queries. At ingestion time, S-RAG constructs a structured representation of the corpus; at inference time, it translates natural-language queries into formal queries over said representation. To validate our approach and promote further research in this area, we introduce two new datasets of aggregative queries: HOTELS and WORLD CUP. Experiments with S-RAG on the newly introduced datasets, as well as on a public benchmark, demonstrate that it substantially outperforms both common RAG systems and long-context LLMs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。