Papers
arxiv:2507.03922

Dynamic Injection of Entity Knowledge into Dense Retrievers

Published on Jul 5
Authors:
,
,
,
,

Abstract

The Knowledgeable Passage Retriever (KPR) enhances BERT-based retrievers with context-entity attention and updatable embeddings, improving retrieval accuracy and achieving state-of-the-art performance on entity-focused datasets.

AI-generated summary

Dense retrievers often struggle with queries involving less-frequent entities due to their limited entity knowledge. We propose the Knowledgeable Passage Retriever (KPR), a BERT-based retriever enhanced with a context-entity attention layer and dynamically updatable entity embeddings. This design enables KPR to incorporate external entity knowledge without retraining. Experiments on three datasets show that KPR consistently improves retrieval accuracy, achieving a substantial 12.6% gain on the EntityQuestions dataset over the model without KPR extensions. When built on the off-the-shelf bge-base retriever, KPR achieves state-of-the-art performance among similarly sized models on two datasets. Code and models will be released soon.

Community

Sign up or log in to comment

Models citing this paper 5

Browse 5 models citing this paper

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2507.03922 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2507.03922 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.