RAG-Instruct：利用多样化检索增强指令提升大语言模型
RAG-Instruct: Boosting LLMs with Diverse Retrieval-Augmented Instructions
AI总结：
本文提出RAG-Instruct方法，通过五种RAG范式和指令模拟从任意语料库合成多样化高质量RAG指令数据，构建40K数据集，显著提升LLMs的零样本RAG能力并优于多种基线。
摘要：
检索增强生成（RAG）已成为通过引入外部知识来增强大语言模型（LLMs）的关键范式。然而，当前的RAG方法面临两个局限：（1）它们仅覆盖有限的RAG场景。（2）由于缺乏通用的RAG数据集，它们的任务多样性受限。为了解决这些局限，我们提出了RAG-Instruct，一种基于任意源语料库合成多样化且高质量RAG指令数据的通用方法。我们的方法利用（1）五种RAG范式，涵盖多样化的查询-文档关系，以及（2）指令模拟，通过利用现有指令数据集的优势来增强指令多样性和质量。使用该方法，我们从Wikipedia构建了一个40K指令数据集，全面覆盖多样化的RAG场景和任务。实验表明，RAG-Instruct有效增强了LLMs的RAG能力，实现了强大的零样本性能，并在多样化的任务集上显著优于各种RAG基线。RAG-Instruct已在https://github.com/FreedomIntelligence/RAG-Instruct公开提供。
英文摘要：
Retrieval-Augmented Generation (RAG) has emerged as a key paradigm for enhancing large language models (LLMs) by incorporating external knowledge. However, current RAG methods face two limitations: (1) they only cover limited RAG scenarios. (2) They suffer from limited task diversity due to the lack of a general RAG dataset. To address these limitations, we propose RAG-Instruct, a general method for synthesizing diverse and high-quality RAG instruction data based on any source corpus. Our approach leverages (1) five RAG paradigms, which encompass diverse query-document relationships, and (2) instruction simulation, which enhances instruction diversity and quality by utilizing the strengths of existing instruction datasets. Using this method, we construct a 40K instruction dataset from Wikipedia, comprehensively covering diverse RAG scenarios and tasks. Experiments demonstrate that RAG-Instruct effectively enhances LLMs' RAG capabilities, achieving strong zero-shot performance and significantly outperforming various RAG baselines across a diverse set of tasks. RAG-Instruct is publicly available at https://github.com/FreedomIntelligence/RAG-Instruct.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
