从检索到推理：面向企业数据的五级RAG能力框架
From Search to Reasoning: A Five-Level RAG Capability Framework for Enterprise Data
AI总结：
本文提出一个面向企业数据的五级RAG能力分类框架（L1-L5），并引入对齐基准，评估四个平台，强调多空间检索和动态编排对实现L1-L4能力的关键价值。
摘要：
检索增强生成（RAG）已成为回答企业数据问题的标准范式。传统上，RAG侧重于基于文本的语义搜索和重排序。然而，当面对超出数据汇总或非文本数据的问题时，这种方法显得不足。这导致了各种尝试来补充RAG，以弥合RAG（实现范式）与企业用户期望其解决的问题（问答问题）之间的差距。鉴于当代RAG是一系列技术的集合而非一种明确的实现，对RAG及相关问答系统的讨论受益于一种面向问题的理解。我们提出一个新的分类框架（L1-L5），根据底层问答问题的数据模态和任务复杂性对系统进行分类：从L1（非结构化数据的表层知识）到L4（反思性和推理知识），以及愿景中的L5（通用智能）。我们还引入了与这些级别对齐的基准，并评估了四个最先进的平台：LangChain、Azure AI Search、OpenAI和Corvic AI。我们的实验强调了多空间检索和动态编排在实现L1-L4能力方面的价值。我们使用代表企业用例的多样化数据集实证验证了我们的发现。
英文摘要：
Retrieval-Augmented Generation (RAG) has emerged as the standard paradigm for answering questions on enterprise data. Traditionally, RAG has centered on text-based semantic search and re-ranking. However, this approach falls short when dealing with questions beyond data summarization or non-text data. This has led to various attempts to supplement RAG to bridge the gap between RAG, the implementation paradigm, and the question answering problem that enterprise users expect it to solve. Given that contemporary RAG is a collection of techniques rather than a defined implementation, discussion of RAG and related question-answering systems benefits from a problem-oriented understanding. We propose a new classification framework (L1-L5) to categorize systems based on data modalities and task complexity of the underlying question answering problems: L1 (Surface Knowledge of Unstructured Data) through L4 (Reflective and Reasoned Knowledge) and the aspirational L5 (General Intelligence). We also introduce benchmarks aligned with these levels and evaluate four state-of-the-art platforms: LangChain, Azure AI Search, OpenAI, and Corvic AI. Our experiments highlight the value of multi-space retrieval and dynamic orchestration for enabling L1-L4 capabilities. We empirically validate our findings using diverse datasets indicative of enterprise use cases.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
