Retrieval-Augmented Generation for Large Language Models: A Survey
Yunfan Gao, Yun Xiong, Xinyu Gao, Kangxiang Jia, Jinliu Pan + 5 more
TLDR
This survey reviews Retrieval-Augmented Generation (RAG) techniques that enhance large language models by integrating external knowledge sources to improve accuracy and reliability.
Key contributions
- Comprehensive overview of RAG paradigms: Naive, Advanced, and Modular approaches.
- Detailed analysis of key RAG components: retrieval, generation, and augmentation techniques.
- Presentation of current evaluation frameworks, benchmarks, challenges, and future research directions.
Why it matters
As large language models struggle with hallucinations and outdated knowledge, RAG offers a crucial method to ground their outputs in external, up-to-date information, improving trustworthiness and applicability in knowledge-intensive tasks. This survey consolidates the state-of-the-art in RAG, guiding researchers and practitioners toward more effective and transparent language generation systems.
Original Abstract
Large Language Models (LLMs) showcase impressive capabilities but encounter challenges like hallucination, outdated knowledge, and non-transparent, untraceable reasoning processes. Retrieval-Augmented Generation (RAG) has emerged as a promising solution by incorporating knowledge from external databases. This enhances the accuracy and credibility of the generation, particularly for knowledge-intensive tasks, and allows for continuous knowledge updates and integration of domain-specific information. RAG synergistically merges LLMs' intrinsic knowledge with the vast, dynamic repositories of external databases. This comprehensive review paper offers a detailed examination of the progression of RAG paradigms, encompassing the Naive RAG, the Advanced RAG, and the Modular RAG. It meticulously scrutinizes the tripartite foundation of RAG frameworks, which includes the retrieval, the generation and the augmentation techniques. The paper highlights the state-of-the-art technologies embedded in each of these critical components, providing a profound understanding of the advancements in RAG systems. Furthermore, this paper introduces up-to-date evaluation framework and benchmark. At the end, this article delineates the challenges currently faced and points out prospective avenues for research and development.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.