Retrieval-Augmented Generation for AI-Generated Content: A Survey
Генерация с дополнением извлечённой информацией для контента, создаваемого искусственным интеллектом: обзор
2026-01-02
SCID: 54.1/qvskdmea
Discuss with AI
AI-generated contentRAG benchmarksinformation retrievalmultimodal applicationsretrieval-augmented generation
Figures from the paper
Abstract (AI)
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 techniques 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 enhancement methods for RAG, facilitating effective engineering and implementation of RAG systems. Then from another view, we survey 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.
Key Findings
1
Integrating information retrieval with generation improves AIGC accuracy and robustness by supplying relevant objects from available data stores.
2
RAG addresses key AIGC challenges, including knowledge updating, long-tail data handling, data leakage mitigation, and high training or inference costs.
3
The paper summarizes additional RAG enhancement methods and surveys practical applications across multiple modalities and tasks.
4
The survey classifies RAG foundations by how retrievers augment generators, providing a unified abstraction across different retrievers, generators, and RAG scenarios.
5
The survey introduces RAG benchmarks, identifies limitations of current systems, and outlines potential directions for future research.
Research Object
retrieval-augmented generation (RAG) integrated into artificial intelligence-generated content (AIGC) scenarios
Research Subject
RAG foundations, enhancement methods, practical applications, benchmarks, limitations, and future directions for improving AIGC generation
Publication Details
Publication Date
2026-01-02
Journal
Publisher
ISSN
Cited by
978
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai20
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer2019
LLaMA: Open and Efficient Foundation Language Models2023
Generative adversarial networks2020
Dense Passage Retrieval for Open-Domain Question Answering2020
Retrieval-Augmented Generation for Large Language Models: A Survey2023
Lost in the Middle: How Language Models Use Long Contexts2024
CodeBERT: A Pre-Trained Model for Programming and Natural Languages2020
GPT-4 Technical Report2023
Scaling Laws for Neural Language Models2020
Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering2021
Evaluating Large Language Models Trained on Code2021
REALM: Retrieval-Augmented Language Model Pre-Training2020
Efficient Transformers: A Survey2022
Active Retrieval Augmented Generation2023
Atlas: Few-shot Learning with Retrieval Augmented Language Models2022
A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models2024
Benchmarking Retrieval-Augmented Generation for Medicine2024
Benchmarking Large Language Models in Retrieval-Augmented Generation2024
In-Context Retrieval-Augmented Language Models2023
Large-Scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation2023
Cited by11
A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models2024
LightRAG: Simple and Fast Retrieval-Augmented Generation2025
Graph Retrieval-Augmented Generation: A Survey2025
From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review2026
Retrieval augmented generation for large language models in healthcare: A systematic review2025
A Survey on Large Language Models for Code Generation2025
Clinical entity augmented retrieval for clinical information extraction2025
Retrieval-Augmented Generation (RAG)2025
Generative AI for Facial Expressions in 3D Game Characters: A Retrieval-Augmented Approach2025
Toward Sustainable Agentic AI Systems: A Survey of Architectures and Methodologies2026
The impact of large language models on collaborative learning processes and outcomes in higher education for English translation2026