示例1: entity_types: [author, publication date, methodology, technology, evaluation method, research direction] text: Title: A Survey on Retrieval-Augmented Text Generation for Large Language Models Authors: Yizheng Huang, Jimmy Huang Published: 2024-04-17 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 that can influence its performance, this paper organizes the RAG paradigm into four categories: pre-retrieval, retrieval, post-retrieval, and generation, offering a detailed perspective from the retrieval viewpoint. It outlines RAG's evolution and discusses the field's progression through the analysis of significant studies. Additionally, the paper introduces evaluation methods for RAG, addressing the challenges faced and proposing future research directions. By offering an organized framework and categorization, the study aims to consolidate existing research on RAG, clarify its technological underpinnings, and highlight its potential to broaden the adaptability and applications of LLMs. PDF Link: http://arxiv.org/pdf/2404.10981v1 ouput: ############################# -实际数据- ###################### entity_types: [author, publication date, methodology, technology, evaluation method, research direction] text: {input_text} ###################### output:
("entity"{tuple_delimiter}A Survey on Retrieval-Augmented Text Generation for Large Language Models{tuple_delimiter}title{tuple_delimiter}The title of the paper discussing Retrieval-Augmented Generation for large language models){record_delimiter} ("entity"{tuple_delimiter}Yizheng Huang, Jimmy Huang{tuple_delimiter}authors{tuple_delimiter}The authors of the paper on Retrieval-Augmented Generation){record_delimiter} ("entity"{tuple_delimiter}2024-04-17{tuple_delimiter}published date{tuple_delimiter}The date the paper on Retrieval-Augmented Generation was published){record_delimiter} ... ("relationship"{tuple_delimiter}A Survey on Retrieval-Augmented Text Generation for Large Language Models{tuple_delimiter}http://arxiv.org/pdf/2404.10981v1{tuple_delimiter}The title of the paper is linked to its PDF version{tuple_delimiter}10){record_delimiter} {completion_delimiter}
SUCCESS: Local Search Response: ### 最新关于RAG的调查
最近，关于检索增强生成（Retrieval-Augmented Generation, RAG）的调查引起了计算语言学界的广泛关注。与传统的生成模型相比，RAG在许多自然语言处理（NLP）任务中显示出显著的优势，并取得了最先进的性能。以下是关于RAG的最新调查的详细信息。调查概述调查论文《A Survey on Retrieval-Augmented Text Generation for Large Language Models》由Yizheng Huang和Jimmy Huang撰写，于2024年4月17日发表。该论文详细探讨了RAG如何结合检索方法与深度学习进展，以解决大型语言模型（LLMs）的静态限制问题，通过动态整合最新的外部信息来增强模型的准确性和可靠性。RAG的四个分类论文将RAG范式分为四个主要类别：预检索、检索、后检索和生成。这种分类从检索的角度提供了对RAG性能影响因素的详细视角，并讨论了该领域的进展。未来研究方向此外，该论文还介绍了RAG的评估方法，并提出了未来的研究方向，旨在通过提供一个有组织的框架和分类，来整合现有的RAG研究，阐明其技术基础，并突出其扩大LLMs适应性和应用的潜力。这些信息提供了关于RAG的最新调查的全面概述，展示了其在NLP领域中的重要性和未来的发展潜力。以上信息参考了以下数据记录：
粤ICP备14082021号
免费POC，
零成本试错
