English

Generative Dense Retrieval: Memory Can Be a Burden

Information Retrieval 2024-01-22 v1 Computation and Language

Abstract

Generative Retrieval (GR), autoregressively decoding relevant document identifiers given a query, has been shown to perform well under the setting of small-scale corpora. By memorizing the document corpus with model parameters, GR implicitly achieves deep interaction between query and document. However, such a memorizing mechanism faces three drawbacks: (1) Poor memory accuracy for fine-grained features of documents; (2) Memory confusion gets worse as the corpus size increases; (3) Huge memory update costs for new documents. To alleviate these problems, we propose the Generative Dense Retrieval (GDR) paradigm. Specifically, GDR first uses the limited memory volume to achieve inter-cluster matching from query to relevant document clusters. Memorizing-free matching mechanism from Dense Retrieval (DR) is then introduced to conduct fine-grained intra-cluster matching from clusters to relevant documents. The coarse-to-fine process maximizes the advantages of GR's deep interaction and DR's scalability. Besides, we design a cluster identifier constructing strategy to facilitate corpus memory and a cluster-adaptive negative sampling strategy to enhance the intra-cluster mapping ability. Empirical results show that GDR obtains an average of 3.0 R@100 improvement on NQ dataset under multiple settings and has better scalability.

Keywords

Cite

@article{arxiv.2401.10487,
  title  = {Generative Dense Retrieval: Memory Can Be a Burden},
  author = {Peiwen Yuan and Xinglin Wang and Shaoxiong Feng and Boyuan Pan and Yiwei Li and Heda Wang and Xupeng Miao and Kan Li},
  journal= {arXiv preprint arXiv:2401.10487},
  year   = {2024}
}

Comments

EACL 2024 main

R2 v1 2026-06-28T14:21:11.460Z