将RAG设计转化为架构搜索问题，系统化优化其超参数配置。
RAISE: RAG Design as an Architecture Search Problem
- 把RAG的多种设计选择建模为可搜索的架构空间。
- 在7个数据集上测试13种搜索算法，发现性能高度依赖任务。
- 提供标准化基准，支持可复现的RAG优化研究。
检索增强生成（RAG）系统涉及查询重写、文本切块、检索深度、重排序和上下文压缩等多种设计选择。实践中这些配置常依赖启发式方法，导致跨场景评估与复现困难。本文提出将该问题建模为RAG架构搜索。为此，我们构建了RAG智能搜索引擎（RAISE），一个全面的框架与基准，用于标准化搜索空间与预算下的RAG超参数优化评估。RAISE实现了13种搜索算法，在7个公开文本与多模态数据集上，使用3个随机种子进行评估。实验表明，优化性能高度依赖任务：在某一数据集表现优异的方法在其他数据集上未必有效，警示不应将平均排名视为普适最优策略。RAISE为RAG超参数优化提供了公平、可复现、系统化的研究基础。
原文摘要 · Abstract (English)
Retrieval-augmented generation (RAG) systems expose numerous design choices spanning query rewriting, chunking, retrieval depth, reranking, and context compression. In practice, these choices are often configured through heuristics, hindering systematic evaluation and reproducibility across settings. We argue that this challenge is best formulated as RAG architecture search. To support controlled and reproducible study of this problem, we introduce the RAG Intelligence Search Engine (RAISE), a comprehensive framework and benchmark for RAG hyperparameter optimization, which evaluates optimization methods for RAG pipelines under standardized search spaces and budgets. RAISE implements 13 search algorithms and evaluates them across seven public text and multimodal datasets using three random seeds. Our experiments show that optimization performance is highly task-dependent: methods that perform strongly on one dataset may not generalize consistently across others, cautioning against interpreting aggregate rankings as evidence of universally superior strategies. RAISE provides a common experimental substrate for fair, reproducible, and systematic research on RAG hyperparameter optimization.
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。