用实体关系模型统一整合异构数据源，提升RAG的检索效率与准确率。
ER-RAG: Enhance RAG with ER-Based Unified Modeling of Heterogeneous Data Sources
- 基于实体-关系模型构建统一接口，支持跨源检索与关联查询。
- 在KDDCup挑战中三项夺冠，较混合方法提升3.1%评分，检索速度加快5.5倍。
- 适合低资源或黑盒环境，便于多源数据融合与模型微调。
大语言模型在问答任务中表现优异，检索增强生成（RAG）通过引入网页、数据库、知识图谱等外部证据提升了精度。然而现有RAG方法对各数据源采用独立策略，难以应对低资源或黑盒场景，且当证据分散时操作复杂。为此，本文提出ER-RAG框架，利用实体-关系（ER）模型统一异构数据源的证据整合。该框架通过基于ER的API实现标准化实体检索与关系查询，支持GET和JOIN操作。采用两阶段生成流程：首先由偏好优化模块选择最优数据源，再由另一模块根据源模式构建API链。该统一机制支持高效微调与无缝集成。ER-RAG在2024年KDDCup CRAG挑战赛中包揽三项冠军，使用8B LLM主干达到与商业RAG系统相当性能，相较混合方法提升3.1%的LLM评分，检索加速5.5倍。
原文摘要 · Abstract (English)
Large language models (LLMs) excel in question-answering (QA) tasks, and retrieval-augmented generation (RAG) enhances their precision by incorporating external evidence from diverse sources like web pages, databases, and knowledge graphs. However, current RAG methods rely on agent-specific strategies for individual data sources, posing challenges low-resource or black-box environments and complicates operations when evidence is fragmented across sources. To address these limitations, we propose ER-RAG, a framework that unifies evidence integration across heterogeneous data sources using the Entity-Relationship (ER) model. ER-RAG standardizes entity retrieval and relationship querying through ER-based APIs with GET and JOIN operations. It employs a two-stage generation process: first, a preference optimization module selects optimal sources; second, another module constructs API chains based on source schemas. This unified approach allows efficient fine-tuning and seamless integration across diverse data sources. ER-RAG demonstrated its effectiveness by winning all three tracks of the 2024 KDDCup CRAG Challenge, achieving performance on par with commercial RAG pipelines using an 8B LLM backbone. It outperformed hybrid competitors by 3.1% in LLM score and accelerated retrieval by 5.5X.
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。