Large language models (LLMs) inevitably exhibit hallucinations since the
accuracy of generated texts cannot be secured solely by the parametric
knowledge they encapsulate. Although retrieval-augmented generation (RAG) is a
practicable complement to LLMs, it relies heavily on the relevance of retrieved
documents, raising concerns about how the model behaves if retrieval goes
wrong. To this end, we propose the Corrective Retrieval Augmented Generation
(CRAG) to improve the robustness of generation. Specifically, a lightweight
retrieval evaluator is designed to assess the overall quality of retrieved
documents for a query, returning a confidence degree based on which different
knowledge retrieval actions can be triggered. Since retrieval from static and
limited corpora can only return sub-optimal documents, large-scale web searches
are utilized as an extension for augmenting the retrieval results. Besides, a
decompose-then-recompose algorithm is designed for retrieved documents to
selectively focus on key information and filter out irrelevant information in
them. CRAG is plug-and-play and can be seamlessly coupled with various
RAG-based approaches. Experiments on four datasets covering short- and
long-form generation tasks show that CRAG can significantly improve the
performance of RAG-based approaches.

大语言模型（LLMs）不可避免地产生幻觉，因为仅依靠它们所封装的参数知识无法确保生成的文本的准确性。为了改善生成的鲁棒性，我们提出了纠正检索增强生成（CRAG）。通过设计轻量级的检索评估模型来评估检索文档的整体质量，并基于此返回信心度，从而触发不同的知识检索操作。此外，利用大规模网络搜索扩展检索结果。通过分解和重组算法，选择性关注关键信息并过滤掉不相关信息。CRAG 与各种基于 RAG 的方法可以无缝连接。在涵盖短文和长文生成任务的四个数据集上的实验表明，CRAG 可以显著提高基于 RAG 的方法的性能。