arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2305.07402cs.CLcs.IR
收藏

搜索与大语言模型在信息检索中的协同作用

Synergistic Interplay between Search and Large Language Models for Information Retrieval

Peking University(北京大学);Microsoft Cooperation(微软公司)

Jiazhan Feng, Chongyang Tao, Xiubo Geng, Tao Shen, Can Xu, Guodong Long, Dongyan Zhao, Daxin Jiang

AI总结:

本研究针对信息检索场景,提出InteR框架实现检索模型与大语言模型的协同优化,通过双向迭代扩充输入提升检索精度,在多类基准任务上取得优于现有方法的零样本检索效果。

摘要:

信息检索(IR)在从海量数据中定位相关资源方面发挥着关键作用,其应用已从传统知识库演进为现代检索模型(RMs)。大语言模型(LLMs)的出现进一步革新了信息检索领域,使用户能够用自然语言与搜索系统交互。本文探讨了大语言模型和检索模型的优缺点,强调了它们在理解用户查询和检索最新信息方面的各自优势。为了在规避两类范式局限性的同时利用二者的优势,我们提出了InteR——一种通过检索模型与大语言模型的协同实现信息优化的新型框架。InteR允许检索模型利用大语言模型生成的知识库扩展查询中的知识,同时使大语言模型能够利用检索到的文档优化提示词构建。这种迭代优化过程扩充了检索模型和大语言模型的输入,从而实现更精准的检索。在涉及网页搜索和低资源检索任务的大规模检索基准上的实验表明,与现有最优方法(甚至那些使用相关性判断的方法)相比,InteR在整体上取得了更优的零样本检索性能。源代码可在https://github.com/Cyril-JZ/InteR获取。

英文摘要:

Information retrieval (IR) plays a crucial role in locating relevant resources from vast amounts of data, and its applications have evolved from traditional knowledge bases to modern retrieval models (RMs). The emergence of large language models (LLMs) has further revolutionized the IR field by enabling users to interact with search systems in natural languages. In this paper, we explore the advantages and disadvantages of LLMs and RMs, highlighting their respective strengths in understanding user-issued queries and retrieving up-to-date information. To leverage the benefits of both paradigms while circumventing their limitations, we propose InteR, a novel framework that facilitates information refinement through synergy between RMs and LLMs. InteR allows RMs to expand knowledge in queries using LLM-generated knowledge collections and enables LLMs to enhance prompt formulation using retrieved documents. This iterative refinement process augments the inputs of RMs and LLMs, leading to more accurate retrieval. Experiments on large-scale retrieval benchmarks involving web search and low-resource retrieval tasks demonstrate that InteR achieves overall superior zero-shot retrieval performance compared to state-of-the-art methods, even those using relevance judgment. Source code is available at https://github.com/Cyril-JZ/InteR

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。

↑