不依赖图结构的实体感知检索，提升问答准确率并减少冗余内容。
SlimRAG: Retrieval without Graphs via Entity-Aware Context Selection
- 用实体-段落映射表替代复杂图结构，实现轻量级检索。
- 在多个问答基准上超越基线模型，索引大小和内容冗余降低60%以上。
- 适合追求高效精准知识检索的应用场景，如智能客服与文档问答。
检索增强生成（RAG）通过推理时引入外部知识提升语言模型性能。然而，基于图的RAG系统常因结构开销大、检索不准而受限：需昂贵的实体链接与关系抽取流程，却仍频繁返回包含松散关联或无关内容的子图。根本原因在于语义相似不等于语义相关。本文提出SlimRAG，一种无需图结构的轻量级检索框架。在索引阶段，基于语义嵌入构建紧凑的实体-段落映射表；在查询阶段，识别关键实体，检索并评分相关段落，组装简洁且语义相关的输入，无需图遍历或边构建。为衡量检索效率，提出相对索引令牌利用率（RITU），量化检索内容紧凑性。跨多个问答基准实验表明，SlimRAG在准确率上优于强基线模型，同时显著降低索引大小与RITU（如16.31对比56+），凸显无结构、以实体为中心的上下文选择价值。代码即将开源。
原文摘要 · Abstract (English)
Retrieval-Augmented Generation (RAG) enhances language models by incorporating external knowledge at inference time. However, graph-based RAG systems often suffer from structural overhead and imprecise retrieval: they require costly pipelines for entity linking and relation extraction, yet frequently return subgraphs filled with loosely related or tangential content. This stems from a fundamental flaw -- semantic similarity does not imply semantic relevance. We introduce SlimRAG, a lightweight framework for retrieval without graphs. SlimRAG replaces structure-heavy components with a simple yet effective entity-aware mechanism. At indexing time, it constructs a compact entity-to-chunk table based on semantic embeddings. At query time, it identifies salient entities, retrieves and scores associated chunks, and assembles a concise, contextually relevant input -- without graph traversal or edge construction. To quantify retrieval efficiency, we propose Relative Index Token Utilization (RITU), a metric measuring the compactness of retrieved content. Experiments across multiple QA benchmarks show that SlimRAG outperforms strong flat and graph-based baselines in accuracy while reducing index size and RITU (e.g., 16.31 vs. 56+), highlighting the value of structure-free, entity-centric context selection. The code will be released soon. https://github.com/continue-ai-company/SlimRAG
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。