Active Retrieval Augmented Generation
https://papers.cool/arxiv/2305.06983
Authors: Zhengbao Jiang ; Frank F. Xu ; Luyu Gao ; Zhiqing Sun ; Qian Liu ; Jane Dwivedi-Yu ; Yiming Yang ; Jamie Callan ; Graham Neubig
Summary: Despite the remarkable ability of large language models (LMs) to comprehend and generate language, they have a tendency to hallucinate and create factually inaccurate output. Augmenting LMs by retrieving information from external knowledge resources is one promising solution. Most existing retrieval augmented LMs employ a retrieve-and-generate setup that only retrieves information once based on the input. This is limiting, however, in more general scenarios involving generation of long texts, where continually gathering information throughout generation is essential. In this work, we provide a generalized view of active retrieval augmented generation, methods that actively decide when and what to retrieve across the course of the generation. We propose Forward-Looking Active REtrieval augmented generation (FLARE), a generic method which iteratively uses a prediction of the upcoming sentence to anticipate future content, which is then utilized as a query to retrieve relevant documents to regenerate the sentence if it contains low-confidence tokens. We test FLARE along with baselines comprehensively over 4 long-form knowledge-intensive generation tasks/datasets. FLARE achieves superior or competitive performance on all tasks, demonstrating the effectiveness of our method. Code and datasets are available at https://github.com/jzbjyb/FLARE.
A: 这篇论文试图解决的问题是大型语言模型(LMs)在理解和生成语言时存在的幻觉(hallucination)问题,即它们倾向于创造事实上不准确的内容。为了解决这个问题,作者提出了一种增强LMs的方法,即通过从外部知识资源中检索信息来辅助生成过程。具体来说,论文提出了一种名为前瞻性主动检索增强生成(Forward-Looking Active REtrieval augmented generation,简称FLARE)的方法,该方法在生成过程中主动决定何时以及检索什么信息。FLARE通过迭代地使用即将生成的句子的预测来预测未来内容,并将其用作查询以检索相关文档,以便在生成包含低置信度标记的句子时重新生成该句子。这种方法旨在提高长文本生成任务中的语言模型性能,特别是在需要持续收集信息的场景中。
A: 相关研究主要集中在以下几个方面:
这些研究为FLARE方法提供了理论基础和技术背景,FLARE在此基础上进一步提出了一种新的主动检索策略,以期在长文本生成任务中取得更好的性能。