arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.01219cs.CL
收藏

检索增强生成最佳实践的探索

Searching for Best Practices in Retrieval-Augmented Generation

School of Computer Science, Fudan University(复旦大学计算机科学学院);Shanghai Key Laboratory of Intelligent Information Processing(上海智能信息处理重点实验室)
Xiaohua Wang, Zhenghua Wang, Xuan Gao, Feiran Zhang, Yixin Wu, Zhibo Xu, Tianyuan Shi, Zhengyuan Wang, Shizheng Li, Qi Qian, Ruicheng Yin, Changze Lv, Xiaoqing … 展开作者

Xiaohua Wang, Zhenghua Wang, Xuan Gao, Feiran Zhang, Yixin Wu, Zhibo Xu, Tianyuan Shi, Zhengyuan Wang, Shizheng Li, Qi Qian, Ruicheng Yin, Changze Lv, Xiaoqing Zheng, Xuanjing Huang

AI总结:

本文通过系统实验探索现有RAG方法及其组合,提出兼顾性能与效率的最佳部署策略,并展示多模态检索与“检索即生成”策略对视觉问答和多模态内容生成的显著提升作用。

摘要:

检索增强生成(RAG)技术已被证明在整合最新信息、减少幻觉以及提升回答质量方面十分有效,尤其是在专业领域中。尽管已经提出了许多 RAG 方法来通过依赖查询的检索增强大语言模型,但这些方法仍然面临实现复杂和响应时间较长的问题。通常,一个 RAG 工作流包含多个处理步骤,每个步骤都可以通过不同方式执行。本文研究了现有的 RAG 方法及其潜在组合,以识别最优的 RAG 实践。通过大量实验,我们提出了若干部署 RAG 的策略,以在性能与效率之间取得平衡。此外,我们证明了多模态检索技术能够显著提升关于视觉输入的问答能力,并利用“检索即生成”策略加速多模态内容的生成。

英文摘要:

Retrieval-augmented generation (RAG) techniques have proven to be effective in integrating up-to-date information, mitigating hallucinations, and enhancing response quality, particularly in specialized domains. While many RAG approaches have been proposed to enhance large language models through query-dependent retrievals, these approaches still suffer from their complex implementation and prolonged response times. Typically, a RAG workflow involves multiple processing steps, each of which can be executed in various ways. Here, we investigate existing RAG approaches and their potential combinations to identify optimal RAG practices. Through extensive experiments, we suggest several strategies for deploying RAG that balance both performance and efficiency. Moreover, we demonstrate that multimodal retrieval techniques can significantly enhance question-answering capabilities about visual inputs and accelerate the generation of multimodal content using a "retrieval as generation" strategy.

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。

↑