面向AI生成内容的检索增强生成:一项综述
Retrieval-Augmented Generation for AI-Generated Content: A Survey
AI总结:
该综述梳理了检索增强生成(RAG)在AI生成内容(AIGC)领域的研究进展,分类归纳RAG基础框架与增强方法,调研其多模态应用,介绍基准测试并指出未来研究方向。
摘要:
模型算法的进步、基础模型的发展以及高质量数据集的获取,推动了人工智能生成内容(Artificial Intelligence Generated Content, AIGC)的演进。尽管AIGC已取得显著成效,但仍面临知识更新、长尾数据处理、缓解数据泄露以及管控高昂训练与推理成本等障碍。检索增强生成(Retrieval-Augmented Generation, RAG)是近期兴起的用于应对上述挑战的范式。具体而言,RAG引入了信息检索流程,通过从可用数据存储中检索相关对象来优化生成过程,从而提升准确率与鲁棒性。本文全面梳理了将RAG技术融入AIGC场景的现有研究。我们首先依据检索器增强生成器的方式对RAG基础进行分类,提炼出适用于各类检索器与生成器的增强方法核心抽象框架。这一统一视角覆盖了所有RAG场景,阐明了助力未来潜在发展的研究进展与关键技术。我们还总结了RAG的额外增强方法,为RAG系统的高效工程化与落地实现提供便利。随后,我们从另一维度调研了RAG在不同模态与任务中的实际应用,为研究人员与从业者提供有价值的参考。此外,我们介绍了RAG的基准测试,讨论了当前RAG系统的局限性,并提出了未来研究的潜在方向。相关代码仓库见GitHub:https://github.com/PKU-DAIR/RAG-Survey。
英文摘要:
Advancements in model algorithms, the growth of foundational models, and access to high-quality datasets have propelled the evolution of Artificial Intelligence Generated Content (AIGC). Despite its notable successes, AIGC still faces hurdles such as updating knowledge, handling long-tail data, mitigating data leakage, and managing high training and inference costs. Retrieval-Augmented Generation (RAG) has recently emerged as a paradigm to address such challenges. In particular, RAG introduces the information retrieval process, which enhances the generation process by retrieving relevant objects from available data stores, leading to higher accuracy and better robustness. In this paper, we comprehensively review existing efforts that integrate RAG technique into AIGC scenarios. We first classify RAG foundations according to how the retriever augments the generator, distilling the fundamental abstractions of the augmentation methodologies for various retrievers and generators. This unified perspective encompasses all RAG scenarios, illuminating advancements and pivotal technologies that help with potential future progress. We also summarize additional enhancements methods for RAG, facilitating effective engineering and implementation of RAG systems. Then from another view, we survey on practical applications of RAG across different modalities and tasks, offering valuable references for researchers and practitioners. Furthermore, we introduce the benchmarks for RAG, discuss the limitations of current RAG systems, and suggest potential directions for future research. Github: https://github.com/PKU-DAIR/RAG-Survey.
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。