mlsanityData to 14 Oct 2026

Dynamic Injection of Entity Knowledge into Dense Retrievers

arXiv 2507.03922 ↗First posted 5 Jul 2025cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

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 demonstrate that KPR consistently improves retrieval accuracy, with particularly large gains on the EntityQuestions dataset. When built on the off-the-shelf bge-base retriever, KPR achieves state-of-the-art performance among similarly sized models on two datasets. Models and code are released at https://github.com/knowledgeable-embedding/knowledgeable-embedding.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 29 of its 48 references that are in the map. First posted on arXiv 5 Jul 2025.

Builds on

29 of 48 references.

References · 29

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2020Scaling Laws for Neural Language Modelscited by 6,586
  4. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  5. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
  6. 2022Locating and Editing Factual Associations in GPTcited by 2,691
  7. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
  8. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,253
  9. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,216
  10. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,128
  11. 2023Towards General Text Embeddings with Multi-stage Contrastive Learningcited by 723
  12. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 692
17 more
  1. 2023C-Pack: Packed Resources For General Chinese Embeddingscited by 578
  2. 2021Datasets: A Community Library for Natural Language Processingcited by 530
  3. 2019ERNIE: Enhanced Language Representation with Informative Entitiescited by 528
  4. 2022Large Language Models Struggle to Learn Long-Tail Knowledgecited by 458
  5. 2020Autoregressive Entity Retrievalcited by 334
  6. 2020LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attentioncited by 326
  7. 2021Simple Entity-Centric Questions Challenge Dense Retrieverscited by 140
  8. 2022RetroMAE: Pre-Training Retrieval-oriented Language Models Via Masked Auto-Encodercited by 118
  9. 2022ReFinED: An Efficient Zero-shot-capable Approach to End-to-End Entity Linkingcited by 74
  10. 2024Theory, Analysis, and Best Practices for Sigmoid Self-Attentioncited by 64
  11. 2018Entity-Duet Neural Ranking: Understanding the Role of Knowledge Graph Semantics in Neural Information Retrievalcited by 33
  12. 2022Towards Best Practices for Training Multilingual Dense Retrieval Modelscited by 26
  13. 2025Scaling Embedding Layers in Language Modelscited by 20
  14. 2017Word-Entity Duet Representations for Document Rankingcited by 16
  15. 2018Mixing Context Granularities for Improved Entity Linking on Question Answering Data across Entity Categoriescited by 9
  16. 2024DyVo: Dynamic Vocabularies for Learned Sparse Retrieval with Entitiescited by 8
  17. 2024DREQ: Document Re-Ranking Using Entity-based Query Understandingcited by 5

Built on by

Not cited yet.