Generative Dense Retrieval: Memory Can Be A Burden

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 s

Stats

• citations3
• S2 citations—
• github stars0
• HF likes0
• heat score4.52
• arxiv keyyuan2024generative

Related papers

• Does Generative Retrieval Overcome The Limitations Of Dense Retrieval? (2025)0.00
• Generative Retrieval As Dense Retrieval (2023)0.00
• Generative Retrieval As Multi-vector Dense Retrieval (2024)8.60
• Generative Retrieval Meets Multi-graded Relevance (2024)2.26
• Continual Learning For Generative Retrieval Over Dynamic Corpora (2023)11.49
• Dense Passage Retrieval: Is It Retrieving? (2024)6.34
• How To Train Your DRAGON: Diverse Augmentation Towards Generalizable Dense Retrieval (2023)11.39
• Generative Recall, Dense Reranking: Learning Multi-view Semantic Ids For Efficient Text-to-video Retrieval (2026)0.00