arXiv cs.AI· Emmanuel Igbekele, Olawande Daramola·· 12 小时前AI 评分26
如何刻画与分析 RAG 技术：一个概念框架
Characterising and Analysing Retrieval-Augmented Generation Techniques
AI 导读
研究者提出一个由主维度和子维度构成的概念框架，用于刻画（定义“是什么”）和分析（定义“效果如何”）现有 RAG 技术，框架基于对文献中 RAG 技术属性的定性分析构建。该框架可作为实证基准测试前的筛选机制，帮助研究者和实践者在计算与资金成本高昂的基准评测之前，选出最符合特定用户与任务需求的 RAG 候选方案。
正文 · 原文
Abstract:The advent of Large Language Models (LLMs) across many application domains has increased the need for Retrieval-Augmented Generation (RAG) to reduce hallucinations and improve LLM performance. Thus far, several RAG techniques with impressive features and capabilities have been proposed in the literature, making it a herculean task to select the most appropriate RAG techniques for specific problem scenarios. Thus, we propose a conceptual framework comprising main dimensions and sub-dimensions for characterising (defining "what it is") and analysing (defining "how well it does") existing RAG techniques. The conceptual framework was developed through a qualitative analysis of the attributes of RAG techniques reported in the literature. It can serve as a pre-empirical filtering mechanism for researchers and practitioners in selecting the highest-fit RAG candidates that meet specific user and task requirements before empirical benchmarking of RAG techniques, which can be computationally and financially expensive.
| Subjects: | Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| MSC classes: | 68Txx 68T50 |
| Cite as: | arXiv:2610.23226 [cs.AI] |
| (or arXiv:2610.23226v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.23226 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Olawande Daramola Prof. [view email]
[v1]
Fri, 16 Oct 2026 09:55:31 UTC (2,437 KB)
来源：arXiv cs.AI · arxiv.org