DACL-RAG：面向检索增强生成的结合课程学习的数据增强策略
DACL-RAG: Data Augmentation Strategy with Curriculum Learning for Retrieval-Augmented Generation
AI总结：
针对RAG训练中检索文档质量参差、区分度低的问题，提出结合多级数据增强与多阶段课程学习的DACL-RAG框架，在四个开放域QA数据集上较现有方法提升2%-4%性能。
摘要：
检索增强生成（RAG）是提升大语言模型（LLM）能力的有效方法。现有方法通常直接使用检索到的前k个文档来优化RAG系统中的检索器或生成器。然而，训练数据中固有的两个关键问题限制了这种训练范式的有效性：（1）不同查询对应的前k个检索文档在内容质量上差异极大，部分能提供有价值的知识，另一些则缺少关键信息甚至具有误导性，以完全随机的方式在这类数据上训练可能会损害生成器提取关键信息的能力；（2）对于给定查询，有限的k个文档集合往往区分度较低，仅在这些文档上训练会让检索器难以学习如何区分相关与不相关文档。为解决这些问题，我们提出DACL-RAG，这是一个多阶段RAG训练框架，结合了多级数据增强策略与多阶段课程学习范式。数据增强策略通过样本演化构建难度可控、全面多样的训练集，课程学习范式则将这些训练集组织为渐进式阶段进行训练，确保稳定持续的性能提升，从而更有效地优化RAG系统的整体性能与泛化能力。我们的DACL-RAG框架在四个开放域问答数据集上展现出一致的有效性，相较于多种先进方法实现了2%到4%的性能提升。
英文摘要：
Retrieval-Augmented Generation (RAG) is an effective method to enhance the capabilities of large language models (LLMs). Existing methods typically optimize the retriever or the generator in a RAG system by directly using the top-k retrieved documents. However, two key issues inherent in the training data constrain the effectiveness of this training paradigm: (1) across different queries, the top-k retrieved documents vary greatly in content quality, with some providing valuable knowledge while others lack critical information or are even misleading, and training on such data in a purely random manner may impair the generator's ability to extract key information; (2) for a given query, the limited set of k documents often exhibits low discriminability, and training solely on them makes it difficult for the retriever to learn how to distinguish between relevant and irrelevant documents. To address these issues, we introduce DACL-RAG, a multi-stage RAG training framework that combines a multi-level Data Augmentation strategy with a multi-stage Curriculum Learning paradigm. The data augmentation strategy constructs comprehensive and diverse training sets with controllable difficulty levels through sample evolution, while the curriculum learning paradigm organizes them into progressive stages for training, ensuring stable and consistent improvements, thereby optimizing the overall performance and generalization of the RAG system more effectively. Our DACL-RAG framework demonstrates consistent effectiveness across four open-domain QA datasets, achieving performance gains of 2% to 4% over multiple advanced methods.
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。
