@inproceedings{yamada-etal-2025-dynamic,
    title = "Dynamic Injection of Entity Knowledge into Dense Retrievers",
    author = "Yamada, Ikuya  and
      Ri, Ryokan  and
      Kojima, Takeshi  and
      Iwasawa, Yusuke  and
      Matsuo, Yutaka",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.915/",
    doi = "10.18653/v1/2025.findings-emnlp.915",
    pages = "16867--16879",
    ISBN = "979-8-89176-335-7",
    abstract = "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."
}