arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.02772cs.IRcs.CL
收藏

GeAR:生成增强检索

GeAR: Generation Augmented Retrieval

Microsoft Corporation(微软公司)

Haoyu Liu, Shaohan Huang, Jianfeng Liu, Yuefeng Zhan, Hao Sun, Weiwei Deng, Feng Sun, Furu Wei, Qi Zhang

AI总结:

提出GeAR方法,通过对比学习提升全局相似度并引入融合与解码模块生成相关上下文,实现细粒度局部信息检索,在不增加计算成本下展现竞争力并提供结果解释新见解。

摘要:

文档检索技术对于开发大规模信息系统至关重要。常见方法是使用双编码器计算查询与文档间的语义相似度。然而,标量相似度往往无法反映足够信息,阻碍了对检索结果的解释。此外,该过程主要关注全局语义,忽略了查询与文档内容之间更细粒度的语义关系。本文提出了一种新方法生成增强检索(GeAR),它不仅通过对比学习提升全局文档-查询相似度,还集成了精心设计的融合与解码模块。这使得GeAR能基于给定查询在文档内生成相关上下文,从而促进局部细粒度信息的检索学习。此外,作为检索器使用时,GeAR不会比双编码器增加任何额外计算成本。GeAR在多种场景和任务中展现出极具竞争力的检索性能。此外,定性分析及GeAR生成的结果为解释检索结果提供了新见解。代码、数据和模型将发布于https://github.com/microsoft/LMOps。

英文摘要:

Document retrieval techniques are essential for developing large-scale information systems. The common approach involves using a bi-encoder to compute the semantic similarity between a query and documents. However, the scalar similarity often fail to reflect enough information, hindering the interpretation of retrieval results. In addition, this process primarily focuses on global semantics, overlooking the finer-grained semantic relationships between the query and the document's content. In this paper, we introduce a novel method, $\textbf{Ge}$neration $\textbf{A}$ugmented $\textbf{R}$etrieval ($\textbf{GeAR}$), which not only improves the global document-query similarity through contrastive learning, but also integrates well-designed fusion and decoding modules. This enables GeAR to generate relevant context within the documents based on a given query, facilitating learning to retrieve local fine-grained information. Furthermore, when used as a retriever, GeAR does not incur any additional computational cost over bi-encoders. GeAR exhibits competitive retrieval performance across diverse scenarios and tasks. Moreover, qualitative analysis and the results generated by GeAR provide novel insights into the interpretation of retrieval results. The code, data, and models will be released at \href{https://github.com/microsoft/LMOps}{https://github.com/microsoft/LMOps}.

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。

↑