DRAGIN: Dynamic Retrieval Augmented Generation based on the Information Needs of Large Language Models

Weihang Su, Yichen Tang, Qingyao Ai*, Zhijing Wu, Yiqun Liu

*此作品的通讯作者

科研成果: 书/报告/会议事项章节会议稿件同行评审

1 引用 (Scopus)

摘要

Dynamic retrieval augmented generation (RAG) paradigm actively decides when and what to retrieve during the text generation process of Large Language Models (LLMs). There are two key elements of this paradigm: identifying the optimal moment to activate the retrieval module (deciding when to retrieve) and crafting the appropriate query once retrieval is triggered (determining what to retrieve). However, current dynamic RAG methods fall short in both aspects. Firstly, the strategies for deciding when to retrieve often rely on static rules. Moreover, the strategies for deciding what to retrieve typically limit themselves to the LLM's most recent sentence or the last few tokens, while the LLM's information needs may span across the entire context. To overcome these limitations, we introduce a new framework, DRAGIN, i.e., Dynamic Retrieval Augmented Generation based on the Information Needs of LLMs. Our framework is specifically designed to make decisions on when and what to retrieve based on the LLM's information needs during the text generation process. We evaluate DRAGIN along with existing methods comprehensively over 4 knowledge-intensive generation datasets. Experimental results show that DRAGIN achieves superior performance on all tasks, demonstrating the effectiveness of our method.

源语言英语
主期刊名Long Papers
编辑Lun-Wei Ku, Andre F. T. Martins, Vivek Srikumar
出版商Association for Computational Linguistics (ACL)
12991-13013
页数23
ISBN(电子版)9798891760943
出版状态已出版 - 2024
活动62nd Annual Meeting of the Association for Computational Linguistics, ACL 2024 - Bangkok, 泰国
期限: 11 8月 202416 8月 2024

出版系列

姓名Proceedings of the Annual Meeting of the Association for Computational Linguistics
1
ISSN(印刷版)0736-587X

会议

会议62nd Annual Meeting of the Association for Computational Linguistics, ACL 2024
国家/地区泰国
Bangkok
时期11/08/2416/08/24

指纹

探究 'DRAGIN: Dynamic Retrieval Augmented Generation based on the Information Needs of Large Language Models' 的科研主题。它们共同构成独一无二的指纹。

引用此

Su, W., Tang, Y., Ai, Q., Wu, Z., & Liu, Y. (2024). DRAGIN: Dynamic Retrieval Augmented Generation based on the Information Needs of Large Language Models. 在 L.-W. Ku, A. F. T. Martins, & V. Srikumar (编辑), Long Papers (页码 12991-13013). (Proceedings of the Annual Meeting of the Association for Computational Linguistics; 卷 1). Association for Computational Linguistics (ACL).