A Survey on Retrieval-Augmented Text Generation for Large Language Models

arXiv:2404.10981v1 Announce Type: cross
Abstract: Retrieval-Augmented Generation (RAG) merges retrieval methods with deep learning advancements to address the static limitations of large language models (LLMs) by enabling the dynamic integration of up-to-date external information. This methodology, focusing primarily on the text domain, provides a cost-effective solution to the generation of plausible but incorrect responses by LLMs, thereby enhancing the accuracy and reliability of their outputs through the use of real-world data. As RAG grows in complexity and incorporates multiple concepts …

abstract arxiv cost cs.ai cs.cl cs.ir deep learning domain dynamic enabling information integration language language models large language large language models limitations llms methodology rag retrieval retrieval-augmented solution survey text text generation type