用问答片段增强生成，让答案可追溯且更精准。
Incorporating Q&A Nuggets into Retrieval-Augmented Generation
- 构建文档问答片段库，用它指导信息抽取与生成
- 在TREC NeuCLIR 2024上，片段召回率、密度和引用准确性均优于Ginger
- 保持全程引用溯源，避免重复，逻辑更清晰
RAGE系统将自动评估（E）的思想融入检索增强生成（RAG）。我们提出Crucible——一种基于问答片段的生成系统，通过从检索到的文档中构建问答片段库，引导信息提取、选择与报告生成。基于片段推理避免了重复信息，凭借清晰可解释的问答语义，取代了模糊的聚类抽象，同时在整个生成过程中保持引用溯源。在TREC NeuCLIR 2024数据集上的评估显示，Crucible系统在片段召回率、密度和引用定位性方面显著优于近期的Ginger系统。
原文摘要 · Abstract (English)
RAGE systems integrate ideas from automatic evaluation (E) into Retrieval-augmented Generation (RAG). As one such example, we present Crucible, a Nugget-Augmented Generation System that preserves explicit citation provenance by constructing a bank of Q&A nuggets from retrieved documents and uses them to guide extraction, selection, and report generation. Reasoning on nuggets avoids repeated information through clear and interpretable Q&A semantics - instead of opaque cluster abstractions - while maintaining citation provenance throughout the entire generation process. Evaluated on the TREC NeuCLIR 2024 collection, our Crucible system substantially outperforms Ginger, a recent nugget-based RAG system, in nugget recall, density, and citation grounding.
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。