对比多种RAG管道，帮用户选最优方案
Evaluating Modern RAG: Textual, Multimodal, Dense, and Late Interaction Pipelines
- 基于实测效果与资源消耗，评估文本、多模态等RAG管道
- 多模态方法提升检索质量，但计算成本更高
- 适合需要权衡精度与效率的系统部署者
检索增强生成（RAG）系统传统上依赖文本管道从文档中提取和检索信息。尽管高效轻量，但此类方法在布局、表格和视觉元素承载语义的文档上表现不佳。近期基于视觉语言模型（VLMs）的多模态管道通过联合编码视觉与文本信号，提升了检索质量，但带来了更高的计算与内存开销。本文提出一种量化、数据驱动的选择方法，帮助实践者根据文档语料库的特性，在实证有效性与资源约束之间选择最合适的RAG管道。我们评估了当前主流的文本与多模态管道，包括密集型与后期交互架构，分析其权衡关系，并提供可操作的指导建议，以平衡检索性能与系统效率。
原文摘要 · Abstract (English)
Retrieval-augmented generation (RAG) systems have traditionally relied on text-based pipelines that extract and retrieve information from documents. While efficient and lightweight, these approaches often struggle with documents where meaning is conveyed through layout, tables, and visual elements. Recent advances in multimodal pipelines, powered by vision-language models (VLMs), improve retrieval quality by jointly encoding visual and textual signals, but at increased computational and memory cost. We propose a quantitative, data-driven selection methodology that guides practitioners in choosing the most appropriate RAG pipeline for a given document corpus based on empirical effectiveness and resource constraints. We evaluate contemporary textual and multimodal pipelines, including dense and late-interaction architectures, analyze their trade-offs, and provide actionable guidance for balancing retrieval performance with system efficiency.
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。