图结构何时值得其成本？检索增强生成中的结构定价案例

中文摘要 AI 辅助

基于图的检索增强生成（RAG）可以帮助回答需要从许多文档中获取信息的问题。然而，构建图通常需要在摄取阶段进行大量语言模型调用。因此，重要的是要问其质量提升是否证明了额外成本的合理性。我们提出了EffiRAG，一个旨在降低这种成本的基于图的RAG系统。它利用图来定位相关段落，并从原始文本生成答案。这种设计保留了源信息，同时使图构建和查询处理保持轻量级。我们在UltraDomain上评估了EffiRAG，该数据集包含来自四个领域的120个开放式问题。与LightRAG-hybrid相比，EffiRAG在93个问题上产生了更受青睐的答案。LightRAG在7个问题上更受青睐，其余20个为平局。EffiRAG还将总系统成本降低了57%，从0.952美元降至0.408美元。该成本包括摄取和查询期间的语言模型调用。随着语料库的增长，这一优势仍然存在。在每个领域10个和20个文档的情况下，EffiRAG使用轻量级的非LLM过滤器来跳过低显著性块。它仍然比LightRAG-hybrid更受青睐。其成本分别低4.2倍和4.5倍。这些比较识别出不同的质量-成本权衡。因此，基于图的RAG系统应通过答案质量和成本两方面进行评估。结果支持能够定位并保留源证据的图结构。

英文摘要

Graph-based retrieval-augmented generation (RAG) can help answer questions that require information from many documents. However, building a graph often requires many language-model calls during ingestion. It is therefore important to ask whether its quality gains justify the additional cost. We present EffiRAG, a graph-based RAG system designed to reduce this cost. It uses the graph to locate relevant passages and generates answers from the original text. This design preserves source information while keeping graph construction and query processing lightweight. We evaluate EffiRAG on UltraDomain, which contains 120 open-ended questions from four domains. Compared with LightRAG-hybrid, EffiRAG produces the preferred answer on 93 questions. LightRAG is preferred on 7, and the remaining 20 are splits. EffiRAG also reduces total system cost by 57 percent, from USD 0.952 to USD 0.408. The cost includes language-model calls during ingestion and querying. The advantage remains as the corpus grows. At 10 and 20 documents per domain, EffiRAG uses a lightweight, non-LLM filter to skip low-salience chunks. It remains preferred over LightRAG-hybrid. It costs 4.2 times and 4.5 times less, respectively. The comparisons identify different quality-cost trade-offs. Graph-based RAG systems should therefore be evaluated by both answer quality and cost. The results favor graph structure that locates and preserves source evidence.

发表机构

• The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））
• The Hong Kong University of Science and Technology（香港科技大学）
• University of Edinburgh（爱丁堡大学）
• Lero, the Research Ireland Centre for Software, University of Limerick（Lero爱尔兰软件研究中心，利默里克大学）
• University of Ottawa（渥太华大学）

机构由 AI 辅助整理，请以论文原文为准。