Retrieval-Augmented Generation (RAG) mitigates issues of the factual errors and hallucinated outputs generated by Large Language Models (LLMs) in open-domain question-answering tasks (OpenQA) via introducing external knowledge. For complex QA, however, existing RAG methods use LLMs to actively predict retrieval timing and directly use the retrieved information for generation, regardless of whether the retrieval timing accurately reflects the actual information needs, or sufficiently considers prior retrieved knowledge, which may result in insufficient information gathering and interaction, yielding low-quality answers. To address these, we propose a generic RAG approach called Adaptive Note-Enhanced RAG (Adaptive-Note) for complex QA tasks, which includes the iterative information collector, adaptive memory reviewer, and task-oriented generator, while following a new Retriever-and-Memory paradigm. Specifically, Adaptive-Note introduces an overarching view of knowledge growth, iteratively gathering new information in the form of notes and updating them into the existing optimal knowledge structure, enhancing high-quality knowledge interactions. In addition, we employ an adaptive, note-based stop-exploration strategy to decide "what to retrieve and when to stop" to encourage sufficient knowledge exploration. We conduct extensive experiments on five complex QA datasets, and the results demonstrate the superiority and effectiveness of our method and its components. The code and data are at https://github.com/thunlp/Adaptive-Note.

翻译：检索增强生成（RAG）通过引入外部知识，缓解了大型语言模型（LLM）在开放域问答任务（OpenQA）中产生事实性错误和幻觉输出的问题。然而，对于复杂问答任务，现有RAG方法使用LLM主动预测检索时机，并直接使用检索到的信息进行生成，无论检索时机是否准确反映了实际信息需求，或是否充分考虑了先前检索到的知识，这可能导致信息收集与交互不足，产生低质量答案。为解决这些问题，我们提出了一种适用于复杂问答任务的通用RAG方法——自适应笔记增强RAG（Adaptive-Note），该方法包含迭代信息收集器、自适应记忆审查器和面向任务的生成器，并遵循一种新的“检索器与记忆”范式。具体而言，Adaptive-Note引入了知识增长的全局视角，以笔记形式迭代收集新信息并将其更新至现有最优知识结构中，从而增强高质量的知识交互。此外，我们采用了一种自适应的、基于笔记的停止探索策略来决定“检索什么以及何时停止”，以鼓励充分的知识探索。我们在五个复杂问答数据集上进行了大量实验，结果证明了我们方法及其各组成部分的优越性和有效性。代码与数据位于 https://github.com/thunlp/Adaptive-Note。