Retrieval-Augmented Generation for AI-Generated Content: A Survey

By Penghao Zhao, Hailin Zhang, Qinhan Yu, Zhengren Wang, Yunteng Geng, Fangcheng Fu, Ling Yang, Wentao Zhang, Bin Cui. Data Science and Engineering, 2024

644 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/ab15463babf98fffc6f683fe2026de0725b5e1a9

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Chaoli Zhang
2. Sunhao Dai
3. Shuaiqiang Wang
4. Bowen Zhang
5. Hengyi Cai
6. Chunping Li
7. Dawei Yin

Citations in the corpus

• Large Language Models for Education: A survey and outlook (2024, positive): “It is based on research emphasizing that effective feed-back should be goal referenced, tangible and transparent, actionable, user-friendly, timely, ongoing, and consistent, ensuring that it meets students’ needs effectively.”
• A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models (2024, positive): “For example, Zhao et al. [156] specifically review multi-modal information-based RAG techniques and Zhao et al. [155] discuss the RAG for AIGC.”
• Graph Retrieval-Augmented Generation: A Survey (2024, neutral): “How did the artistic movements of the 19th century impact the development of modern art in the 20th century?”
• WebThinker: Empowering Large Reasoning Models with Deep Research Capability (2025, neutral): “Retrieval-augmented generation (RAG) enhances generative models by integrating retrieval mechanisms, enabling access to external knowledge beyond static parameters [24, 66, 28, 68].”
• Evaluation of Retrieval-Augmented Generation: A Survey (2024, methodology): “To clarify the elements further, we conducted this survey on RAG evaluation to address the current gaps in the area, which differs from the prior RAG surveys [57,14,21] that predominantly collected specific RAG methods or data.”
• Tool learning with large language models: a survey (2024, positive): “Meanwhile, we also acknowledge the foundational contributions of earlier perspective papers like those by Mialon et al. (2023) [45] and Qin et al. (2023) [16], which initially highlighted the promising opportunities that tools present to enhance LLMs capabilities.”
• Temporal Preference Optimization for Unsupervised Retrieval (2026, unknown): “Copyright 2026 by the author(s). systems (Bobadilla et al., 2013; Zhang et al., 2019; Singh, 2023; Li et al., 2024), question answering (Karpukhin et al., 2020; Zhang et al., 2023a;b), and retrieval-augmented generation (Lewis et al., 2020; Zhao et al., 2024a; Fan et al., 2024; Kwon et al., 2025).”
• Information Retrieval Using Large Language Models on a Restricted Access Environment (2026, unknown): “Some authors modify the chunking strategy, the embedding model, the LLM’s prompt, and the LLM model, as seen in the papers studied in the survey [15].”
• Mycroft - Retrieval Augmented Generation for SDK Documentation (2025, unknown): “Some authors modify the chunking strategy, the embedding model, the LLM’s prompt, and the LLM model, as seen in the papers studied in the survey [14].”
• ArchRAG: Attributed Community-based Hierarchical Retrieval-Augmented Generation (2025, unknown): “To enhance the trustworthiness and interpretability of LLMs, Retrieval-Augmented Generation (RAG) methods [15, 16, 24, 26, 71, 77, 80] have emerged as a core approach, which often retrieve relevant information from documents, relational data, and graph data to facilitate the QA tasks.”
• SimGRAG: Leveraging Similar Subgraphs for Knowledge Graphs Driven Retrieval-Augmented Generation (2024, unknown): “Retrieval-Augmented Generation (RAG) (Gao et al., 2023; Zhao et al., 2024) is a promising solution that retrieves related information from external databases to assist LLMs. Driven by documents, naive RAG approaches divide them into text chunks, which are embedded into dense vectors for retrieval.”
• Pcc-tuning: Breaking the Contrastive Learning Ceiling in Semantic Textual Similarity (2024, methodology): “Finally, in sub-section 4.4, we examine the efficacy of Pcc-tuning under different prompts.”
• Advancing Semantic Textual Similarity Modeling: A Regression Framework with Translated ReLU and Smooth K2 Loss (2024, background): “Contrastive Learning Pre-Trained Models : With the growing importance of embeddings in retrieval-augmented generation (Zhao et al., 2024) and other application scenarios, more companies and institutions are dedicating efforts to developing specialized text representation models.”
• CLARC: C/C++ Benchmark for Robust Code Search (2026, unknown): “Consequently, embedding-based retrieval models remain the standard for scalable navigation, serving as critical components in both standalone search tools and Retrieval-Augmented Generation (RAG) pipelines (Chen et al., 2024; Wang et al., 2025; Zhao et al., 2024).”