检索-生成协同增强的大语言模型
Retrieval-Generation Synergy Augmented Large Language Models
AI总结：
针对大语言模型知识增强时的文档获取问题，提出迭代式检索-生成协作框架，融合两类知识并通过交互辅助多步推理，在4个问答数据集上表现优于现有基线。
摘要：
经任务相关文档增强的大语言模型已在知识密集型任务上展现出出色性能。但在如何获取有效文档方面，现有方法主要分为两类：一类是从外部知识库检索，另一类是利用大语言模型生成文档。我们提出一种迭代式检索-生成协作框架，它既能利用参数化与非参数化知识，还能通过检索-生成交互找到正确推理路径，这对需要多步推理的任务至关重要。我们在4个问答数据集（包括单跳QA和多跳QA任务）上开展了实验。实证结果表明，该方法显著提升了大语言模型的推理能力，性能优于此前的基线模型。
英文摘要：
Large language models augmented with task-relevant documents have demonstrated impressive performance on knowledge-intensive tasks. However, regarding how to obtain effective documents, the existing methods are mainly divided into two categories. One is to retrieve from an external knowledge base, and the other is to utilize large language models to generate documents. We propose an iterative retrieval-generation collaborative framework. It is not only able to leverage both parametric and non-parametric knowledge, but also helps to find the correct reasoning path through retrieval-generation interactions, which is very important for tasks that require multi-step reasoning. We conduct experiments on four question answering datasets, including single-hop QA and multi-hop QA tasks. Empirical results show that our method significantly improves the reasoning ability of large language models and outperforms previous baselines.
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。
