Corrective Retrieval Augmented Generation（纠错式检索增强生成）
Corrective Retrieval Augmented Generation
AI总结：
针对大语言模型幻觉及RAG依赖检索质量的问题，提出即插即用的CRAG方法，通过轻量检索评估器、网页搜索扩展和先分解再重组算法，显著提升各类RAG方法的生成鲁棒性与性能。
摘要：
大语言模型（LLM）不可避免会产生幻觉，因为其生成文本的准确性无法仅靠自身封装的参数化知识来保证。尽管检索增强生成（RAG）是对LLM的一种可行补充，但它高度依赖检索文档的相关性，这引发了人们对检索出错时模型表现的担忧。为此，我们提出Corrective Retrieval Augmented Generation（CRAG，纠错式检索增强生成）以提升生成的鲁棒性。具体而言，我们设计了一个轻量级检索评估器，用于评估针对某一查询的检索文档整体质量，返回置信度，并据此触发不同的知识检索动作。由于从静态且有限的语料库中检索只能返回次优文档，我们利用大规模网页搜索作为扩展来补充检索结果。此外，我们还为检索文档设计了一种先分解再重组的算法，以选择性聚焦关键信息并过滤掉其中的无关信息。CRAG是即插即用的，可与各类基于RAG的方法无缝结合。在涵盖短文本和长文本生成任务的四个数据集上的实验表明，CRAG能够显著提升基于RAG的方法的性能。
英文摘要：
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.
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。
